Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 13220
    Prev
    Next
    INDEX
    Explanations

    instances in the text where the phrase "go out" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "go out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dys
    -0.73
     Primordial
    -0.65
    ERO
    -0.61
    iol
    -0.61
    hiba
    -0.60
    MH
    -0.60
    DN
    -0.59
    aeus
    -0.59
    ulous
    -0.59
    benef
    -0.57
    POSITIVE LOGITS
    fitted
    1.13
     partying
    0.94
    doors
    0.92
     swinging
    0.91
    ta
    0.89
    door
    0.87
     shopping
    0.83
    stretched
    0.82
    smart
    0.81
    fitting
    0.81
    Activations Density 0.039%

    No Known Activations