© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14151
    Prev
    Next
    INDEX
    Explanations

    terms related to financial institutions, particularly those containing the acronym "IN"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "IN" and other prepositions or related terms

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    lets
    -0.69
    angel
    -0.69
    flies
    -0.68
    uffs
    -0.68
    ffen
    -0.67
    ãĤª
    -0.67
    ÃŃn
    -0.67
    auri
    -0.67
    rief
    -0.66
    geons
    -0.65
    POSITIVE LOGITS
    OVA
    1.06
    PUT
    1.04
    TERN
    1.03
    CEPT
    1.01
    OX
    1.00
    FU
    1.00
    IST
    0.99
    ROR
    0.98
    VEN
    0.98
    ER
    0.98
    Activations Density 0.124%

    No Known Activations