© 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. 4001
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the main focus or subject of a text

    oai_token-act-pair · gpt-3.5-turbo

    statements about the nature or quality of something

    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
    dies
    -0.69
     glaciers
    -0.65
    aths
    -0.62
    ths
    -0.62
    ¶æ
    -0.61
    cknow
    -0.60
     looms
    -0.59
    ranean
    -0.59
     Figures
    -0.59
     escapes
    -0.58
    POSITIVE LOGITS
     awfully
    0.76
     definitely
    0.75
     gonna
    0.75
     ONLY
    0.74
     VERY
    0.74
     absolutely
    0.74
     invaluable
    0.73
     deprecated
    0.73
     especially
    0.72
     extremely
    0.72
    Activations Density 0.280%

    No Known Activations