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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 22602
    Prev
    Next
    INDEX
    Explanations

    proper nouns with few common unique words

    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
     banking
    -0.64
     nationally
    -0.64
     disability
    -0.62
     affiliate
    -0.60
     sustainable
    -0.57
     scratch
    -0.56
     lifetime
    -0.56
     establishment
    -0.56
     hon
    -0.56
     aviation
    -0.56
    POSITIVE LOGITS
    xual
    1.41
    cia
    1.33
    ect
    1.20
    enes
    1.11
    anie
    1.10
    gian
    1.10
    ttes
    1.10
    icz
    1.07
    oux
    1.06
    ean
    1.05
    Activations Density 0.570%

    No Known Activations