© 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. 14876
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Dil" with varying levels of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Dilma" and variations of the word "dilute."

    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
    */(
    -0.94
    è¦ļéĨĴ
    -0.88
    é¾įå¥ij士
    -0.79
     Enabled
    -0.77
     Butterfly
    -0.76
    æĸ¹
    -0.75
     Aval
    -0.73
    hips
    -0.72
    lished
    -0.71
     Debor
    -0.68
    POSITIVE LOGITS
    usional
    1.02
    ution
    0.95
    uvian
    0.93
    igent
    0.92
    ancing
    0.91
    awar
    0.90
    utations
    0.90
    gence
    0.89
    ivers
    0.88
    ient
    0.86
    Activations Density 0.016%

    No Known Activations