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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9636
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by location indicators

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or places related to individuals and organizations

    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
     replay
    -0.78
     Replay
    -0.74
     indicators
    -0.70
     headlights
    -0.69
     benefic
    -0.68
     criterion
    -0.67
     thumbs
    -0.66
     elim
    -0.66
     "%
    -0.65
     revers
    -0.65
    POSITIVE LOGITS
    based
    1.57
    area
    1.48
    centric
    1.15
    style
    1.11
    themed
    1.10
    sized
    1.10
    trained
    1.08
    focused
    1.08
    native
    1.07
    born
    1.06
    Activations Density 0.051%

    No Known Activations