© 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. 7-RES-JB
    11. 14391
    Prev
    Next
    INDEX
    Explanations

    social and political terms related to civil rights and government structures

    oai_token-act-pair · gpt-3.5-turbo

    words related to significant societal concepts or issues

    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
     Cutting
    -0.61
     Peel
    -0.60
     hypothal
    -0.59
     experiments
    -0.59
     Optical
    -0.58
     traject
    -0.58
     capacities
    -0.57
     dismantling
    -0.57
     Participants
    -0.57
     faculties
    -0.56
    POSITIVE LOGITS
    âĢİ
    0.80
    orah
    0.80
    beer
    0.78
    vern
    0.76
    Jew
    0.74
    microsoft
    0.72
    __
    0.71
    Semitism
    0.71
    -.
    0.71
    bt
    0.70
    Activations Density 0.193%

    No Known Activations