© 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. 4-RES-JB
    11. 476
    Prev
    Next
    INDEX
    Explanations

    words related to locations, specifically streets or areas

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific sequences of letters or syllables within words

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

    No Comments

    Negative Logits
    olicy
    -0.89
    URES
    -0.84
    ocre
    -0.81
    usalem
    -0.81
    olved
    -0.78
    ascus
    -0.77
    othal
    -0.76
    amsung
    -0.69
    URE
    -0.69
    aido
    -0.68
    POSITIVE LOGITS
    tto
    1.08
    ffect
    0.95
    tta
    0.91
    lette
    0.89
    mand
    0.89
    alle
    0.83
    bum
    0.83
    tti
    0.82
    tt
    0.81
    val
    0.80
    Activations Density 0.008%

    No Known Activations