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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 6601
    Prev
    Next
    INDEX
    Explanations

    names, mostly "Richardson."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals, particularly the name "Richardson."

    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
    plane
    -0.82
    ware
    -0.81
    ãĥĩãĤ£
    -0.70
    abilities
    -0.69
    emonic
    -0.67
    wart
    -0.67
    planes
    -0.67
    arthed
    -0.67
     Clockwork
    -0.64
    anced
    -0.63
    POSITIVE LOGITS
    lisher
    0.77
    orius
    0.75
    ians
    0.71
    erent
    0.67
    iate
    0.67
    uary
    0.67
     alley
    0.66
     Oilers
    0.66
    iah
    0.65
    ober
    0.65
    Activations Density 0.121%

    No Known Activations