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. 4619
    Prev
    Next
    INDEX
    Explanations

    phrases related to being "hung", which can refer to being suspended, undecided, or other contextual meanings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hung" and its variations

    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
    ibel
    -0.78
    utive
    -0.77
    BY
    -0.76
    å§«
    -0.75
    tical
    -0.70
    ignty
    -0.69
    ctive
    -0.66
    ãĥĨãĤ£
    -0.65
    topic
    -0.65
    ãĥ«
    -0.63
    POSITIVE LOGITS
     hung
    1.17
     hanging
    1.00
     hang
    0.97
     exha
    0.82
    rily
    0.82
     hangs
    0.82
     hanged
    0.81
    Hung
    0.80
    ratulations
    0.79
     Hang
    0.75
    Activations Density 0.005%

    No Known Activations