© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 3683
    Prev
    Next
    INDEX
    Explanations

    text related to subscribing to newsletters or emails

    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
    198
    +0.10
    0.6%
    754
    +0.09
    0.5%
    587
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.10
    0.10
    306
    +0.09
    0.10
    699
    +0.09
    0.01
    Negative Logits
    come
    -0.67
    had
    -0.62
    grave
    -0.58
    being
    -0.57
    roo
    -0.56
    comes
    -0.54
    stood
    -0.54
    stru
    -0.54
    equality
    -0.53
    reach
    -0.53
    POSITIVE LOGITS
     Sign
    0.72
     inbox
    0.65
     subscriptions
    0.62
     Typ
    0.61
     Subscribe
    0.60
     Emails
    0.60
     SIGN
    0.59
     subscribers
    0.58
     subscriber
    0.58
     Inqu
    0.57
    Activations Density 7.504%

    No Known Activations