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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 18803
    Prev
    Next
    INDEX
    Explanations

    phrases containing the term "common" used in a negative context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to laws and common practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eki
    -0.89
    psey
    -0.85
     Lumpur
    -0.75
    uliffe
    -0.71
    arching
    -0.69
    yson
    -0.68
    ileaks
    -0.68
    edged
    -0.68
     srf
    -0.67
    zik
    -0.67
    POSITIVE LOGITS
    pmwiki
    0.99
    rences
    0.88
    aceae
    0.86
     occurrence
    0.86
    ensical
    0.82
    runtime
    0.81
     Uncommon
    0.80
     amongst
    0.79
    \">
    0.78
     Errors
    0.76
    Activations Density 0.218%

    No Known Activations