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. 21137
    Prev
    Next
    INDEX
    Explanations

    phrases related to fulfilling commitments or promises

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to following through on commitments or obligations

    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
     Fiesta
    -0.73
     Mages
    -0.66
     Dome
    -0.66
     Maced
    -0.64
    lite
    -0.63
     Spells
    -0.62
     Jung
    -0.62
     Chargers
    -0.61
     Grade
    -0.60
     Mage
    -0.60
    POSITIVE LOGITS
    rodu
    0.77
    chers
    0.73
    ework
    0.73
    uclear
    0.69
    arations
    0.69
    haar
    0.68
    ays
    0.68
    043
    0.67
    olicy
    0.67
    apses
    0.66
    Activations Density 0.174%

    No Known Activations