© 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. 11-RES-JB
    11. 21905
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings or conversations

    oai_token-act-pair · gpt-3.5-turbo

    statements or claims made by individuals or officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "âĢ¦
    -1.36
    "âĢ¦
    -1.36
    âĢ¦"
    -1.17
    âĢ¦
    -1.07
    âĢ¦)
    -1.01
     –
    -0.97
    –
    -0.94
     ðŁĻĤ
    -0.92
    âĢ³
    -0.90
    /"
    -0.80
    POSITIVE LOGITS
    .''
    2.76
    ''.
    2.56
    ''
    2.54
    ,''
    2.53
    �
    2.49
     ''
    2.47
    .�
    2.37
     �
    2.32
    '';
    2.18
    ``
    2.08
    Activations Density 0.150%

    No Known Activations