© 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. 6-RES-JB
    11. 21909
    Prev
    Next
    INDEX
    Explanations

    scientific evidence or research findings

    oai_token-act-pair · gpt-3.5-turbo

    references to evidence or proof in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Evidence

    No Comments

    Negative Logits
    ategory
    -0.75
    ttle
    -0.72
    otom
    -0.68
    skill
    -0.66
    quer
    -0.64
    mist
    -0.64
    cffffcc
    -0.64
     actionGroup
    -0.63
     throats
    -0.63
    isse
    -0.62
    POSITIVE LOGITS
    evidence
    0.99
     evidence
    0.97
    Evidence
    0.90
     Evidence
    0.83
     demonstrating
    0.80
    orial
    0.80
     conclusive
    0.79
     suggesting
    0.79
     corrobor
    0.78
     suggests
    0.77
    Activations Density 0.023%

    No Known Activations