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. 23638
    Prev
    Next
    INDEX
    Explanations

    prompts requesting interaction or action from the reader

    oai_token-act-pair · gpt-3.5-turbo

    requests or prompts for action

    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
    cler
    -0.76
    pires
    -0.71
    arc
    -0.69
     Huntington
    -0.69
    visor
    -0.68
    law
    -0.64
    tin
    -0.64
    lings
    -0.63
    imposed
    -0.63
    borgh
    -0.63
    POSITIVE LOGITS
     advise
    0.90
     note
    0.88
     forgive
    0.84
     enable
    0.83
     sir
    0.82
     beware
    0.82
     dont
    0.80
     Subscribe
    0.80
     fill
    0.78
     pardon
    0.78
    Activations Density 0.016%

    No Known Activations