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. 4-RES-JB
    6. 17428
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to significant events or controversial topics

    oai_token-act-pair · gpt-3.5-turbo

    significant narratives or shocking events

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

    No Comments

    Negative Logits
    cknowled
    -0.63
    reciation
    -0.63
    verning
    -0.62
    versely
    -0.62
    assadors
    -0.61
    appropriately
    -0.59
     trustworthy
    -0.58
    eeper
    -0.58
     GOODMAN
    -0.57
     evenly
    -0.57
    POSITIVE LOGITS
    etheless
    0.71
     imaginable
    0.71
    smanship
    0.71
    ulence
    0.68
    manship
    0.67
    antry
    0.64
     awaits
    0.63
    iasco
    0.63
    ptoms
    0.61
    iosity
    0.61
    Activations Density 0.930%

    No Known Activations