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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6873
    Prev
    Next
    INDEX
    Explanations

    data patterns such as percentages and common indicators

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or statistics

    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
    [/
    -0.51
    ;
    -0.49
     âĢķ
    -0.47
     ·
    -0.46
     UNCLASSIFIED
    -0.46
    ........................
    -0.45
    âĢ¦.
    -0.45
    ,''
    -0.44
    .
    -0.43
    âĢ¦..
    -0.43
    POSITIVE LOGITS
    ¥µ
    0.49
     pione
    0.47
    alks
    0.47
    rians
    0.47
    Roaming
    0.45
    IJ
    0.45
    vice
    0.44
    ActionCode
    0.44
    lling
    0.44
    OME
    0.43
    Activations Density 2.189%

    No Known Activations