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. 3195
    Prev
    Next
    INDEX
    Explanations

    times and time zones in text

    oai_token-act-pair · gpt-3.5-turbo

    timestamps and event-related information

    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
    vim
    -0.81
    backer
    -0.79
    respond
    -0.79
    cer
    -0.77
    shr
    -0.77
    cci
    -0.77
    hm
    -0.76
    escal
    -0.75
    mean
    -0.75
    Wan
    -0.74
    POSITIVE LOGITS
    EST
    1.16
    IFIED
    1.13
    LY
    1.07
    FUL
    1.06
    FORM
    1.00
    ITY
    1.00
    ORY
    0.99
    WOR
    0.97
    REAM
    0.97
    IM
    0.96
    Activations Density 0.029%

    No Known Activations