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. 14914
    Prev
    Next
    INDEX
    Explanations

    dates written in the format "month day, year" with a high emphasis on December 31st

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number "31" in various contexts

    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
    atis
    -0.93
    akespe
    -0.87
    atics
    -0.82
    akens
    -0.80
    ramid
    -0.79
    redit
    -0.78
    rats
    -0.75
    abwe
    -0.74
    retched
    -0.74
    akening
    -0.73
    POSITIVE LOGITS
    st
    0.81
    backer
    0.74
    00
    0.74
    ¯¯
    0.73
    ¯¯¯¯
    0.72
     msec
    0.69
    803
    0.69
    rd
    0.69
    vier
    0.69
    nm
    0.67
    Activations Density 0.028%

    No Known Activations