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. 16089
    Prev
    Next
    INDEX
    Explanations

    instructions or tips beginning with "If you have."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possession or requirements related to the reader's experiences and actions

    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
    "},
    -0.74
    hu
    -0.68
    Els
    -0.67
    ãĥķ
    -0.67
    burgh
    -0.65
    Js
    -0.64
    Dub
    -0.63
    DragonMagazine
    -0.63
    NetMessage
    -0.61
    "},{"
    -0.60
    POSITIVE LOGITS
     unsure
    0.76
     lucky
    0.73
     inclined
    0.70
     DEBUG
    0.68
     unlucky
    0.66
    audi
    0.65
     interested
    0.64
    ileged
    0.64
     yourself
    0.63
     subscrib
    0.63
    Activations Density 0.234%

    No Known Activations