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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11351
    Prev
    Next
    INDEX
    Explanations

    words related to specific phonetic structures, specifically consonant patterns

    oai_token-act-pair · gpt-3.5-turbo

    terms related to consonants and observational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     redes
    -0.80
     toget
    -0.67
     princ
    -0.65
    EStream
    -0.65
    FactoryReloaded
    -0.65
    GD
    -0.60
     Reese
    -0.58
     Hans
    -0.57
     diam
    -0.57
    GAME
    -0.57
    POSITIVE LOGITS
    ants
    1.95
    ances
    1.90
    atory
    1.88
    ant
    1.84
    ations
    1.76
    ance
    1.72
    ancy
    1.71
    ational
    1.68
    ators
    1.60
    ancies
    1.59
    Activations Density 0.140%

    No Known Activations