© 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. 2-RES-JB
    11. 12855
    Prev
    Next
    INDEX
    Explanations

    references to undisclosed or unspecified information

    oai_token-act-pair · gpt-3.5-turbo

    terms related to undisclosed or unspecified amounts and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingo
    -0.84
    ynthesis
    -0.82
    hedral
    -0.79
    aldi
    -0.78
    mong
    -0.77
    acco
    -0.77
    anooga
    -0.76
    =-=-=-=-=-=-=-=-
    -0.73
    chev
    -0.72
    abies
    -0.71
    POSITIVE LOGITS
     unspecified
    0.86
     undisclosed
    0.84
     TBA
    0.74
    =]
    0.73
    theless
    0.71
     amounts
    0.69
    ãĤ¯
    0.69
     NX
    0.69
    ],[
    0.69
    itarian
    0.66
    Activations Density 0.012%

    No Known Activations