© 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. 6699
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a specific individual's perspective or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "for its part" or variations of responsibility claims

    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
    itton
    -0.78
    olesc
    -0.71
    CENT
    -0.70
     millenn
    -0.69
    anth
    -0.67
     perspect
    -0.62
    lishes
    -0.62
     notor
    -0.60
     slicing
    -0.60
     conclud
    -0.58
    POSITIVE LOGITS
    sis
    0.69
    dad
    0.69
    urers
    0.68
    urer
    0.67
    aniel
    0.64
    ographer
    0.62
    reads
    0.62
    played
    0.62
    oof
    0.61
    Benz
    0.61
    Activations Density 0.017%

    No Known Activations