© 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. 10-RES-JB
    11. 7444
    Prev
    Next
    INDEX
    Explanations

    details related to actions and decisions made by different individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to financial transactions and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¹
    -0.69
    ĸļ
    -0.68
    ĺħ
    -0.66
    Ö¼
    -0.66
    ĺ
    -0.65
    Ĥª
    -0.64
    eeks
    -0.63
    ĭ
    -0.63
    Ĥ
    -0.61
    okin
    -0.61
    POSITIVE LOGITS
     whom
    1.04
    ?,
    1.04
     versus
    1.01
     depends
    0.95
     vs
    0.88
     etc
    0.83
    ?",
    0.82
    liest
    0.80
     respectively
    0.79
     next
    0.77
    Activations Density 0.285%

    No Known Activations