© 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. 23449
    Prev
    Next
    INDEX
    Explanations

    references to the sports team "Wolfpack"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Wolf" and related terminology, particularly in contexts involving sports or characters

    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
    nces
    -0.76
    thritis
    -0.75
    bably
    -0.75
    kson
    -0.69
    acists
    -0.69
    iotics
    -0.68
    ursed
    -0.68
    ixel
    -0.67
    ngth
    -0.67
     unnecess
    -0.67
    POSITIVE LOGITS
    enstein
    1.28
    hound
    1.22
    sburg
    1.20
    ram
    1.03
    gang
    1.03
    owitz
    1.02
    pack
    1.01
    endor
    0.96
    rider
    0.95
    bats
    0.94
    Activations Density 0.031%

    No Known Activations