© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11395
    Prev
    Next
    INDEX
    Explanations

    references to vampire characters

    oai_token-act-pair · gpt-3.5-turbo

    references to vampires and vampire-related content

    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
     OS
    -0.87
    Jam
    -0.85
     Iw
    -0.83
    IJ
    -0.82
     Manning
    -0.78
     Kerr
    -0.77
     AFC
    -0.77
     Howe
    -0.76
     Lewis
    -0.76
     OU
    -0.76
    POSITIVE LOGITS
     vampire
    3.28
     vampires
    3.23
     Vampire
    3.12
    ampire
    2.42
     Dracula
    2.36
    ampires
    2.02
     Werewolf
    1.87
     Buffy
    1.70
    wolves
    1.43
     Cullen
    1.39
    Activations Density 0.046%

    No Known Activations