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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 24103
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations and numbers

    oai_token-act-pair · gpt-3.5-turbo

    trends or increases related to statistics or data points

    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
    )).
    -0.76
    ?).
    -0.68
    anooga
    -0.67
    ]).
    -0.67
    ~
    -0.66
     [&
    -0.66
    Was
    -0.65
    â̦"
    -0.64
    )!
    -0.64
    ?".
    -0.64
    POSITIVE LOGITS
     Mehran
    0.74
     Kazakh
    0.69
     poppy
    0.67
     secretive
    0.66
     porous
    0.65
     Nato
    0.65
     licences
    0.65
     defendants
    0.64
     Pakistani
    0.64
     paramilitary
    0.63
    Activations Density 1.714%

    No Known Activations