© 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. 6911
    Prev
    Next
    INDEX
    Explanations

    hyphenated terms with numerical values

    oai_token-act-pair · gpt-3.5-turbo

    negative or critical descriptions related to various topics

    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
     nursing
    -0.81
     plotting
    -0.77
     corros
    -0.76
     deduct
    -0.73
    inic
    -0.72
     subtract
    -0.71
     chains
    -0.71
     wrench
    -0.71
     juveniles
    -0.71
     fren
    -0.70
    POSITIVE LOGITS
    Aid
    1.22
    Tech
    1.10
    Mail
    1.08
    Zero
    1.06
    Country
    1.06
    Strike
    1.05
    Sport
    1.05
    Own
    1.05
    Ex
    1.04
    Line
    1.03
    Activations Density 0.094%

    No Known Activations