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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20761
    Prev
    Next
    INDEX
    Explanations

    statements related to policies, regulations, actions, or states of being

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to regulatory or governmental discussions

    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
    .–
    -0.62
    .</
    -0.62
     ..."
    -0.61
    bury
    -0.60
    -"
    -0.59
    fil
    -0.57
    .","
    -0.57
    croft
    -0.56
    ../
    -0.55
    Mine
    -0.55
    POSITIVE LOGITS
     meanwhile
    1.03
     also
    1.01
     furthermore
    0.99
     moreover
    0.98
     therefore
    0.93
     however
    0.88
     certainly
    0.88
     undoubtedly
    0.84
     thus
    0.78
     doubtless
    0.76
    Activations Density 0.760%

    No Known Activations