© 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. 8-RES-JB
    11. 2762
    Prev
    Next
    INDEX
    Explanations

    percentages mentioned in financial contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to percentages and statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Stra
    -0.67
    plates
    -0.67
    hess
    -0.65
    !/
    -0.62
    swe
    -0.62
    RAW
    -0.60
    Ready
    -0.59
    ä¹ĭ
    -0.58
    LESS
    -0.57
    HUD
    -0.57
    POSITIVE LOGITS
     capita
    0.97
     cent
    0.96
    malink
    0.81
    tains
    0.80
    uters
    0.79
    cill
    0.76
    iev
    0.75
    uvian
    0.73
     lakh
    0.71
    imester
    0.71
    Activations Density 0.034%

    No Known Activations