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. 541
    Prev
    Next
    INDEX
    Explanations

    phrases containing the question "What to do with" something

    oai_token-act-pair · gpt-3.5-turbo

    questions and phrases about what to do in various situations

    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
    mart
    -0.66
    icious
    -0.66
    nas
    -0.63
    journal
    -0.61
    iations
    -0.59
    orah
    -0.59
     asleep
    -0.59
    press
    -0.58
    iation
    -0.57
     Fest
    -0.56
    POSITIVE LOGITS
     regard
    1.20
     regards
    1.16
     impunity
    1.09
    draw
    1.05
     respect
    0.87
    stood
    0.79
    standing
    0.76
     dignity
    0.71
    holding
    0.67
     DRAG
    0.67
    Activations Density 0.094%

    No Known Activations