© 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. 4-RES-JB
    11. 6586
    Prev
    Next
    INDEX
    Explanations

    phrases indicating direct comparisons or contrasts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "to be" in various forms

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

    No Comments

    Negative Logits
     Carnival
    -0.66
     Grape
    -0.62
     FANTASY
    -0.61
     MMO
    -0.60
     Playoff
    -0.60
     Cards
    -0.60
     Pants
    -0.59
     Wear
    -0.59
     Emin
    -0.57
     Griffin
    -0.56
    POSITIVE LOGITS
     presently
    0.69
     hitherto
    0.65
    liest
    0.65
    ragon
    0.62
    oldemort
    0.61
    anyl
    0.61
    iam
    0.60
    angler
    0.60
    ensis
    0.59
    kus
    0.59
    Activations Density 0.206%

    No Known Activations