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. 9182
    Prev
    Next
    INDEX
    Explanations

    adjectives describing physical characteristics or states

    oai_token-act-pair · gpt-3.5-turbo

    adjectives or adverbial forms that end with "ly."

    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
    uther
    -0.90
    ainer
    -0.87
    arte
    -0.85
    aver
    -0.82
    intern
    -0.76
    iffe
    -0.75
    acl
    -0.73
    regon
    -0.72
    avering
    -0.72
    href
    -0.71
    POSITIVE LOGITS
    ly
    0.88
     tones
    0.86
     sounding
    0.85
     affairs
    0.84
     slopes
    0.79
     affair
    0.79
    ulent
    0.79
     terrain
    0.76
     conco
    0.76
     enterprises
    0.75
    Activations Density 0.086%

    No Known Activations