© 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. 11-RES-JB
    11. 22461
    Prev
    Next
    INDEX
    Explanations

    specific parts of long numbers, possibly related to financial amounts

    oai_token-act-pair · gpt-3.5-turbo

    statements about failures or shortcomings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hers
    -0.66
     He
    -0.66
     him
    -0.64
     he
    -0.63
     mascul
    -0.62
     guy
    -0.59
    zona
    -0.58
    iken
    -0.57
     pigeon
    -0.55
    yip
    -0.55
    POSITIVE LOGITS
    âĢ
    1.14
    today
    0.86
    Yesterday
    0.84
    Today
    0.84
    DragonMagazine
    0.82
    Following
    0.82
    AFP
    0.82
    çīĪ
    0.82
    now
    0.81
    ãĢ
    0.80
    Activations Density 0.751%

    No Known Activations