© 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. 6877
    Prev
    Next
    INDEX
    Explanations

    phrases related to causation or prediction of outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causality or outcomes

    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
    oqu
    -0.65
    yd
    -0.63
    pmwiki
    -0.62
    Cas
    -0.59
    advertisement
    -0.59
    kus
    -0.59
    ascus
    -0.59
     Unknown
    -0.57
     Bastard
    -0.57
    Pic
    -0.57
    POSITIVE LOGITS
     someday
    0.86
    enance
    0.81
    geries
    0.81
    igate
    0.78
     tomorrow
    0.72
    gery
    0.71
    rued
    0.69
    lessly
    0.67
     some
    0.67
     sooner
    0.66
    Activations Density 0.321%

    No Known Activations