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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 6-RES-JB
    6. 6204
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    empty or non-content sections in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itars
    -0.82
    uality
    -0.81
     âĢº
    -0.73
    abi
    -0.71
    coins
    -0.69
     solves
    -0.69
    verage
    -0.68
    itto
    -0.67
    amera
    -0.66
    ourney
    -0.66
    POSITIVE LOGITS
     aforementioned
    1.01
     latter
    1.00
     same
    0.94
     likes
    0.91
     respective
    0.90
     slightest
    0.88
     afore
    0.86
     United
    0.86
     outset
    0.85
     Clintons
    0.84
    Activations Density 0.141%

    No Known Activations