© 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. 14118
    Prev
    Next
    INDEX
    Explanations

    text related to labels or labeling on various products or objects

    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
    +0.23
    1.1%
    679
    +0.11
    0.5%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    101
    +0.23
    0.21
    756
    +0.11
    -0.12
    338
    +0.10
    0.10
    Negative Logits
    issance
    -0.67
    vati
    -0.65
    ILLE
    -0.65
    tein
    -0.64
    ashington
    -0.63
    gm
    -0.61
     odds
    -0.60
    olars
    -0.58
    aldo
    -0.58
    DAY
    -0.57
    POSITIVE LOGITS
     label
    0.86
     labels
    0.85
    cloth
    0.79
    mates
    0.77
    mate
    0.76
    strip
    0.75
    red
    0.71
    mark
    0.71
    ovo
    0.70
    label
    0.70
    Activations Density 8.477%

    No Known Activations