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. 1-RES-JB
    6. 19171
    Prev
    Next
    INDEX
    Explanations

    instances of the word "goes" followed by a number indicating the strength of the activation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "goes" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    role
    -0.74
    eers
    -0.71
    uctor
    -0.71
    rient
    -0.67
    icon
    -0.67
    cos
    -0.66
    essor
    -0.65
    icons
    -0.62
    eer
    -0.62
    itionally
    -0.62
    POSITIVE LOGITS
    Ń·
    0.96
    verning
    0.86
    vt
    0.83
     Forth
    0.83
    lems
    0.81
    itters
    0.80
    OHN
    0.73
     ashore
    0.73
    uten
    0.73
    ģĸ
    0.71
    Activations Density 0.014%

    No Known Activations