© 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. 9-RES-JB
    11. 4741
    Prev
    Next
    INDEX
    Explanations

    scientific studies or research findings

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to demonstrating or showing evidence in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eks
    -0.69
    naissance
    -0.69
     Pastebin
    -0.68
    pee
    -0.68
    tesy
    -0.67
     Vanity
    -0.67
    nor
    -0.66
    abus
    -0.65
    urch
    -0.65
    taboola
    -0.65
    POSITIVE LOGITS
     correlations
    1.09
     convinc
    0.97
     abnormalities
    0.94
     conclusive
    0.84
     correlation
    0.84
     reversible
    0.84
     that
    0.81
     widespread
    0.81
     heterogeneity
    0.81
     how
    0.81
    Activations Density 0.171%

    No Known Activations