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. 14155
    Prev
    Next
    INDEX
    Explanations

    words related to strong beliefs or commitments

    oai_token-act-pair · gpt-3.5-turbo

    intensifying or emphasizing adjectives and adverbs

    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
     costumes
    -0.69
    ysc
    -0.68
    wich
    -0.66
    acan
    -0.65
     Hatch
    -0.65
     minors
    -0.64
     Solitaire
    -0.64
    izons
    -0.63
     bathrooms
    -0.62
     skins
    -0.62
    POSITIVE LOGITS
    ocal
    0.89
     insistence
    0.85
    ãģ®å®
    0.82
     pounding
    0.76
     adherence
    0.76
    ailed
    0.76
     refusal
    0.74
     repud
    0.74
    enting
    0.71
    ignt
    0.69
    Activations Density 0.144%

    No Known Activations