© 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. 16779
    Prev
    Next
    INDEX
    Explanations

    phrases expressing surprise or realization

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing surprise or disbelief

    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
    Dialogue
    -0.81
    adr
    -0.72
    ribut
    -0.70
    Rel
    -0.69
    gp
    -0.64
    ioxide
    -0.63
    utic
    -0.62
    verend
    -0.61
    rough
    -0.60
    bis
    -0.60
    POSITIVE LOGITS
     beforehand
    0.75
     bothered
    0.70
     Saban
    0.70
     Bout
    0.64
     existed
    0.63
     myself
    0.63
     Kamp
    0.63
     intending
    0.62
    terday
    0.62
     spoiled
    0.61
    Activations Density 0.317%

    No Known Activations