© 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. 3-RES-JB
    11. 15261
    Prev
    Next
    INDEX
    Explanations

    numbered lists or rankings

    oai_token-act-pair · gpt-3.5-turbo

    references to rankings or positions, often related to lists or ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heric
    -0.68
    ãĥ¼ãĥĨ
    -0.67
    oÄŁ
    -0.67
     unravel
    -0.66
    range
    -0.66
     gain
    -0.65
     valley
    -0.64
    abase
    -0.63
     rest
    -0.63
     Commonwealth
    -0.61
    POSITIVE LOGITS
    CB
    0.93
    JB
    0.79
    MF
    0.71
    milo
    0.71
    JV
    0.70
    JD
    0.70
    FH
    0.69
    ################################
    0.69
    ecd
    0.68
    orah
    0.68
    Activations Density 0.071%

    No Known Activations