© 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. 0-RES-JB
    11. 6270
    Prev
    Next
    INDEX
    Explanations

    references to a person named Terrence

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Ter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SHIP
    -0.82
    iously
    -0.75
    lessly
    -0.70
    fix
    -0.68
    gins
    -0.68
    aeus
    -0.68
    qa
    -0.67
    rf
    -0.67
    opian
    -0.67
    boot
    -0.66
    POSITIVE LOGITS
     Ter
    3.72
    Ter
    2.27
     ter
    2.17
     TER
    1.54
     Terr
    1.45
     Terra
    1.35
     terr
    1.34
     Tur
    1.21
     Terran
    1.16
     Tem
    1.16
    Activations Density 0.019%

    No Known Activations