© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 22703
    Prev
    Next
    INDEX
    Explanations

    phrases related to capturing attention or interest

    oai_token-act-pair · gpt-3.5-turbo

    references to attracting attention or interest

    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
    enhagen
    -0.72
     nomine
    -0.65
    die
    -0.65
    ĸļ
    -0.64
    arth
    -0.64
    arcity
    -0.63
    appa
    -0.62
    andi
    -0.62
    ĪĴ
    -0.61
     honored
    -0.61
    POSITIVE LOGITS
     drift
    0.78
     whiff
    0.78
     attention
    0.77
    ById
    0.76
    Exception
    0.76
     glimpse
    0.73
     scent
    0.68
     brunt
    0.67
     itch
    0.65
    tails
    0.65
    Activations Density 0.109%

    No Known Activations