© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 12375
    Prev
    Next
    INDEX
    Explanations

    phrases indicating upcoming or imminent events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating something is imminent or about to happen

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BT
    -0.73
    Newsletter
    -0.70
    mie
    -0.67
    à©
    -0.66
    mi
    -0.62
    è¦
    -0.61
    \<
    -0.61
    ãĥ
    -0.60
    Ü
    -0.59
    rences
    -0.59
    POSITIVE LOGITS
     halfway
    0.96
     to
    0.83
     midway
    0.69
     eighty
    0.67
     ready
    0.63
     thirty
    0.63
    population
    0.62
     seventy
    0.62
    joy
    0.61
     parity
    0.61
    Activations Density 0.055%

    No Known Activations