© 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. 20203
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific details such as names, dates, and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific events, locations, or significant terms associated with activities or happenings

    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
    ĨĴ
    -0.80
    elta
    -0.66
     jugg
    -0.62
    Ãį
    -0.61
    ibal
    -0.61
    adi
    -0.61
    idel
    -0.60
    ÃŃ
    -0.59
     Imm
    -0.58
    iber
    -0.58
    POSITIVE LOGITS
    on
    1.25
     ON
    1.21
     on
    1.19
    ons
    1.07
    On
    1.05
     On
    1.02
    ON
    0.99
    ONS
    0.93
    onian
    0.93
     onto
    0.93
    Activations Density 0.144%

    No Known Activations