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. 4-RES-JB
    6. 12876
    Prev
    Next
    INDEX
    Explanations

    references to fairy tales and related mythical elements

    oai_token-act-pair · gpt-3.5-turbo

    references to fairy tales and fantastical elements

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

    No Comments

    Negative Logits
    iferation
    -0.86
    aeda
    -0.83
    upon
    -0.82
    ĵĺ
    -0.79
    ebus
    -0.78
    atility
    -0.77
    ricted
    -0.75
    CHAT
    -0.72
    arcity
    -0.72
    İĭ
    -0.71
    POSITIVE LOGITS
    tale
    1.29
     tale
    1.09
     fairy
    1.02
     tales
    0.96
     Tale
    0.91
     Fairy
    0.87
     princess
    0.84
    ãĥ«
    0.76
    tailed
    0.75
    lla
    0.73
    Activations Density 0.017%

    No Known Activations