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. 1-RES-JB
    6. 10175
    Prev
    Next
    INDEX
    Explanations

    mentions of a person named "Eddie" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    instances of the abbreviation "dd" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Crimean
    -0.70
    GROUND
    -0.70
     Revolutionary
    -0.68
    OURCE
    -0.67
     Pastebin
    -0.65
    displayText
    -0.61
     MIA
    -0.60
     Korean
    -0.60
    VALUE
    -0.60
     Isis
    -0.59
    POSITIVE LOGITS
    dd
    1.47
    entimes
    1.01
    edd
    0.95
    cffff
    0.91
    ragon
    0.90
    etermin
    0.88
    orf
    0.88
    itional
    0.87
    iamond
    0.86
    sd
    0.83
    Activations Density 0.002%

    No Known Activations