© 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. 18527
    Prev
    Next
    INDEX
    Explanations

    words related to web and digital communications

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "cc"

    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
     Lans
    -0.81
    chest
    -0.78
     Skydragon
    -0.66
     Roosevelt
    -0.65
    haul
    -0.65
    cknow
    -0.62
    ãĥĦ
    -0.62
    TRY
    -0.61
    ãĥ³ãĤ¸
    -0.60
    ãĤ¤
    -0.60
    POSITIVE LOGITS
    entric
    1.28
    arthy
    1.12
    aneers
    1.10
    lesi
    1.02
    artney
    0.96
    uracy
    0.94
    inct
    0.93
    lesiastical
    0.93
    inelli
    0.93
    uzz
    0.88
    Activations Density 0.031%

    No Known Activations