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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17556
    Prev
    Next
    INDEX
    Explanations

    phrases related to names and titles

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific names related to people and places

    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
    FUL
    -0.71
    INGTON
    -0.67
    lessness
    -0.65
    pless
    -0.62
    bilt
    -0.62
    place
    -0.56
    lihood
    -0.56
    ãĥ£
    -0.56
    #$
    -0.56
    FORMATION
    -0.55
    POSITIVE LOGITS
    o
    2.10
    os
    1.55
    i
    1.50
    a
    1.31
    oing
    1.31
    ino
    1.26
    ini
    1.24
    oi
    1.21
    oes
    1.20
    oa
    1.17
    Activations Density 0.251%

    No Known Activations