© 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. 6-RES-JB
    11. 11718
    Prev
    Next
    INDEX
    Explanations

    numeric values preceded by special characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols commonly used in various contexts, particularly related to language processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ograph
    -0.82
    estate
    -0.79
    imer
    -0.76
    imore
    -0.74
    ovie
    -0.73
    ogene
    -0.72
    adium
    -0.69
    ipop
    -0.69
    arella
    -0.68
    iple
    -0.68
    POSITIVE LOGITS
    s
    0.93
    ternity
    0.79
    lette
    0.77
    lio
    0.74
    ð
    0.74
    ths
    0.73
    tions
    0.71
    ÙĨ
    0.70
    TION
    0.70
    scribed
    0.69
    Activations Density 0.020%

    No Known Activations