© 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. 7-RES-JB
    11. 13418
    Prev
    Next
    INDEX
    Explanations

    instances where actions are done automatically or without manual intervention

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "automatically" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.96
    ippi
    -0.79
    andals
    -0.79
    tons
    -0.78
    ergus
    -0.77
    ador
    -0.76
    Liter
    -0.75
    rug
    -0.74
    ,,,,
    -0.74
    raints
    -0.74
    POSITIVE LOGITS
     detect
    0.86
     induct
    0.85
     migrate
    0.84
     populate
    0.82
     generated
    0.80
     detects
    0.80
    immune
    0.80
     upd
    0.79
     identifiable
    0.79
     assume
    0.79
    Activations Density 0.024%

    No Known Activations