© 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. 4240
    Prev
    Next
    INDEX
    Explanations

    verbs related to achieving success or accomplishing something

    oai_token-act-pair · gpt-3.5-turbo
    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
    seed
    -0.70
    liner
    -0.70
     reserved
    -0.69
     towels
    -0.68
     bases
    -0.66
     crates
    -0.63
    forward
    -0.61
     onions
    -0.61
    othy
    -0.60
    çļ
    -0.59
    POSITIVE LOGITS
     miser
    0.99
    awaru
    0.93
     tremend
    0.76
     academ
    0.74
    isSpecialOrderable
    0.74
    ively
    0.73
    iage
    0.73
     brilliantly
    0.70
    enance
    0.69
     therein
    0.68
    Activations Density 0.028%

    No Known Activations