Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 2195
    Prev
    Next
    INDEX
    Explanations

    phrases related to progress or advancement

    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
    pmwiki
    -0.69
    uded
    -0.68
    iciency
    -0.67
    ilies
    -0.65
    bryce
    -0.63
    iuses
    -0.61
    atur
    -0.60
    krit
    -0.59
    ateur
    -0.59
    unts
    -0.58
    POSITIVE LOGITS
     forward
    1.41
     forwards
    1.20
     toward
    1.16
     towards
    1.16
     onward
    1.11
    forward
    1.10
     ahead
    1.03
     Forward
    1.02
     onwards
    0.95
     backwards
    0.94
    Activations Density 0.143%

    No Known Activations