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. 9-RES-JB
    6. 21736
    Prev
    Next
    INDEX
    Explanations

    references to the timeframe of "last year" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to specific quantities or figures related to different topics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hod
    -0.58
     ASAP
    -0.58
    amination
    -0.56
    pty
    -0.55
     Selection
    -0.55
     Concepts
    -0.53
    THING
    -0.53
    Often
    -0.53
     awhile
    -0.53
    ometime
    -0.53
    POSITIVE LOGITS
     alone
    1.12
     compared
    0.95
    according
    0.93
     combined
    0.77
     Including
    0.77
     attributable
    0.75
     according
    0.75
     includ
    0.74
    *.
    0.73
     (£
    0.73
    Activations Density 0.196%

    No Known Activations