© 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. 0-RES-JB
    11. 22221
    Prev
    Next
    INDEX
    Explanations

    references to a specific entity or brand named "Fine" with varying levels of importance attached to the mentions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Fine" and variations of it in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chang
    -0.79
    GBT
    -0.75
     cla
    -0.74
    aunts
    -0.74
     brim
    -0.73
     Babel
    -0.70
     blink
    -0.70
     dynam
    -0.68
     interoper
    -0.68
     battalion
    -0.68
    POSITIVE LOGITS
     Fine
    3.31
    Fine
    2.32
    fine
    1.58
     Gross
    1.30
     Fey
    1.21
     Muse
    1.04
     Fur
    1.01
     Darling
    0.96
     Dise
    0.93
     Tao
    0.92
    Activations Density 0.020%

    No Known Activations