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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16005
    Prev
    Next
    INDEX
    Explanations

    numerical values related to time, particularly the number 72

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly related to measurements or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yang
    -0.87
    BOOK
    -0.86
    gets
    -0.70
    eering
    -0.69
    achu
    -0.69
    feature
    -0.69
    furt
    -0.68
    fan
    -0.67
    lace
    -0.67
    ezvous
    -0.67
    POSITIVE LOGITS
     ILCS
    0.94
    00
    0.82
    icum
    0.82
    80
    0.82
    00000
    0.81
    ipop
    0.81
    icably
    0.81
    ITY
    0.75
    velength
    0.75
    ocally
    0.74
    Activations Density 0.034%

    No Known Activations