© 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. 7-RES-JB
    11. 23541
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the name "Se" or "Seventh"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Se" or similar repeated context indicating a specific subject or character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.75
     diplom
    -0.71
     banter
    -0.67
    uracy
    -0.66
     CPC
    -0.63
    iants
    -0.63
     anecd
    -0.63
    INGTON
    -0.63
     treating
    -0.62
     resting
    -0.62
    POSITIVE LOGITS
    eker
    1.36
    vere
    1.25
    gments
    1.25
    asons
    1.20
    ldom
    1.17
    infeld
    1.14
    verson
    1.12
    gregation
    1.12
    venth
    1.10
    gment
    1.09
    Activations Density 0.017%

    No Known Activations