© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 1169
    Prev
    Next
    INDEX
    Explanations

    legal and law enforcement-related actions and events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal actions and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Space
    -0.63
    usterity
    -0.60
    Effect
    -0.57
    grow
    -0.56
    ALTH
    -0.54
    xs
    -0.54
    bert
    -0.54
    pac
    -0.54
    act
    -0.53
     billion
    -0.53
    POSITIVE LOGITS
    etheless
    0.97
     additionally
    0.93
     again
    0.84
     nonetheless
    0.83
    again
    0.81
     ALSO
    0.79
     secondly
    0.78
     furthermore
    0.76
     rul
    0.71
     also
    0.71
    Activations Density 0.957%

    No Known Activations