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. 11577
    Prev
    Next
    INDEX
    Explanations

    phrases indicating departure or sudden action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "off" indicating departure or movement away

    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
    ancial
    -0.83
    Export
    -0.70
    MX
    -0.69
     teasp
    -0.69
    ounty
    -0.68
    elsius
    -0.68
    Gall
    -0.64
    olson
    -0.64
    ļéĨĴ
    -0.63
    inity
    -0.63
    POSITIVE LOGITS
    screen
    0.90
    site
    0.83
     pist
    0.81
    stage
    0.79
    shoot
    0.78
     leash
    0.77
    spr
    0.76
     Broadway
    0.74
    cffffcc
    0.73
    loaded
    0.73
    Activations Density 0.044%

    No Known Activations