© 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. 9827
    Prev
    Next
    INDEX
    Explanations

    dates and events mentioned in text with varying levels of detail

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to financial transactions and investments

    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
     Ross
    -0.71
     Blair
    -0.69
     Xiao
    -0.67
     Saul
    -0.67
     Hanson
    -0.67
     Samar
    -0.66
     Weld
    -0.66
     Tenn
    -0.66
     Horizon
    -0.65
     Solomon
    -0.65
    POSITIVE LOGITS
    photos
    1.23
    gallery
    1.20
    dead
    1.17
    guide
    1.14
    basketball
    1.12
    committee
    1.12
    det
    1.09
    prot
    1.09
    reve
    1.09
    201
    1.07
    Activations Density 0.071%

    No Known Activations