© 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. 40720
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues and criminal activities

    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
    +0.30
    1.6%
    481
    +0.12
    0.6%
    154
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.30
    0.38
    14
    +0.12
    0.07
    554
    +0.08
    -0.17
    Negative Logits
    arser
    -0.63
    iti
    -0.60
    eur
    -0.60
    vironment
    -0.58
    trop
    -0.57
     permitting
    -0.56
    osphere
    -0.56
    grain
    -0.55
     drip
    -0.55
    wide
    -0.55
    POSITIVE LOGITS
    selves
    0.91
     selves
    0.84
     jointly
    0.76
     reunion
    0.74
     together
    0.71
     respective
    0.69
     Together
    0.69
     twins
    0.67
     brothers
    0.67
     siblings
    0.66
    Activations Density 20.486%

    No Known Activations