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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    6. 20003
    Prev
    Next
    INDEX
    Explanations

    words related to being a fan or having a strong liking for something

    oai_token-act-pair · gpt-3.5-turbo

    words related to fandom and enthusiasm for various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unfocusedRange
    -0.73
    ateral
    -0.67
     Kob
    -0.65
    eneg
    -0.64
     Proceedings
    -0.63
    innon
    -0.62
    NESS
    -0.61
    apeake
    -0.60
     Labrador
    -0.60
    PP
    -0.59
    POSITIVE LOGITS
    atical
    1.14
    atics
    1.04
     fan
    0.98
    club
    0.96
    catentry
    0.92
    Fan
    0.92
    Fans
    0.92
     Fan
    0.91
    fare
    0.88
    atically
    0.88
    Activations Density 0.015%

    No Known Activations