© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 14222
    Prev
    Next
    INDEX
    Explanations

    positive and motivating content related to personal achievement and success

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.22
    1.0%
    634
    +0.12
    0.5%
    38
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.22
    0.17
    718
    +0.12
    0.21
    634
    +0.11
    0.17
    Negative Logits
     reportedly
    -0.76
     cx
    -0.68
    lict
    -0.67
     allegedly
    -0.65
     meanwhile
    -0.65
    isi
    -0.62
     alleges
    -0.60
     backdrop
    -0.60
    arthed
    -0.60
     accompan
    -0.59
    POSITIVE LOGITS
     underest
    0.94
     underestimated
    0.94
     somew
    0.94
     underestimate
    0.91
     overest
    0.82
     subconscious
    0.77
     misunder
    0.76
     misunderstanding
    0.76
     miscon
    0.76
     typo
    0.75
    Activations Density 22.058%

    No Known Activations