© 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. 4-RES-JB
    11. 2750
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical codes like 401, 501, 503, and 421

    oai_token-act-pair · gpt-3.5-turbo

    references to retirement and tax-related programs or accounts

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

    No Comments

    Negative Logits
    alone
    -0.69
    boards
    -0.66
     Establishment
    -0.63
    athering
    -0.62
    effic
    -0.61
    riel
    -0.61
     symmetry
    -0.60
     exercised
    -0.60
    estine
    -0.60
    ulatory
    -0.59
    POSITIVE LOGITS
    \\\\\\\\
    1.00
    º
    0.75
    ħĭ
    0.74
    )</
    0.71
    ²¾
    0.71
    BUG
    0.69
    rf
    0.68
    ANY
    0.68
    yz
    0.68
    yll
    0.68
    Activations Density 0.018%

    No Known Activations