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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8509
    Prev
    Next
    INDEX
    Explanations

    numerical sequences involving the number 123

    oai_token-act-pair · gpt-3.5-turbo

    the sequence of numbers starting with "123", particularly in various contexts like statistics or identifiers

    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
    ãħĭ
    -0.76
     Confederacy
    -0.69
    iewicz
    -0.69
    lication
    -0.68
     Opposition
    -0.68
    abwe
    -0.66
     GOODMAN
    -0.66
     Chill
    -0.64
     Helpful
    -0.63
     KKK
    -0.62
    POSITIVE LOGITS
    456
    1.18
    RF
    1.00
     ILCS
    0.94
    123
    0.92
    rance
    0.86
    kefeller
    0.86
    inct
    0.86
    45
    0.85
    urious
    0.85
    nard
    0.85
    Activations Density 0.015%

    No Known Activations