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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 6219
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to public figures and organizations

    oai_token-act-pair · gpt-3.5-turbo

    prominent names and titles associated with educational institutions and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ettel
    -0.66
     pse
    -0.65
     brute
    -0.64
    ļ
    -0.61
     pedals
    -0.60
     toile
    -0.60
    âĶĢâĶĢâĶĢâĶĢ
    -0.59
     doct
    -0.57
     torture
    -0.57
     misery
    -0.57
    POSITIVE LOGITS
    okane
    0.72
     Classification
    0.66
     Horizons
    0.62
     Properties
    0.61
     Frontier
    0.59
     Construction
    0.59
     Evaluation
    0.59
    ®,
    0.59
     Development
    0.59
     Region
    0.58
    Activations Density 1.472%

    No Known Activations