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. 5-RES-JB
    6. 14292
    Prev
    Next
    INDEX
    Explanations

    references to horns, particularly those related to rhinoceros horns

    oai_token-act-pair · gpt-3.5-turbo

    references to horns, particularly in relation to rhinoceroses

    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
    ricular
    -0.79
    anmar
    -0.76
    ultz
    -0.73
    tun
    -0.72
    ĵĺ
    -0.71
    essen
    -0.71
    tube
    -0.70
    locks
    -0.70
    ombat
    -0.70
    safe
    -0.70
    POSITIVE LOGITS
     horns
    0.79
    frog
    0.75
     horn
    0.71
    aurus
    0.70
    ophone
    0.67
    ensed
    0.67
     Messi
    0.63
    OGR
    0.63
     cir
    0.61
     deaf
    0.61
    Activations Density 0.063%

    No Known Activations