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. 6082
    Prev
    Next
    INDEX
    Explanations

    dates in the format 'dd/mm/yyyy'

    oai_token-act-pair · gpt-3.5-turbo

    dates and numerical information, particularly those related to July 2007

    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
     tremend
    -0.82
    anguage
    -0.75
     exha
    -0.74
    iliated
    -0.73
     allergies
    -0.69
    anus
    -0.69
     notor
    -0.68
     eleph
    -0.68
     livest
    -0.67
    pora
    -0.67
    POSITIVE LOGITS
    00
    1.19
    05
    1.02
    01
    1.01
    08
    1.00
    005
    0.98
    07
    0.97
    06
    0.96
    003
    0.96
    004
    0.93
    09
    0.91
    Activations Density 0.013%

    No Known Activations