© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 389
    Prev
    Next
    INDEX
    Explanations

    the word "fantasy" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "fantasy" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umen
    -0.77
     Respond
    -0.75
     Inspect
    -0.69
     Tup
    -0.69
     Burr
    -0.68
    apsed
    -0.67
    umin
    -0.67
     Stores
    -0.66
     Cong
    -0.65
    sever
    -0.65
    POSITIVE LOGITS
     fantasy
    3.78
     Fantasy
    2.71
     fantasies
    2.30
    antasy
    2.25
     FANTASY
    2.08
     fantas
    1.67
     fiction
    1.48
    olkien
    1.29
     fairy
    1.28
     dystopian
    1.26
    Activations Density 0.007%

    No Known Activations