© 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. 0-RES-JB
    6. 16820
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Squad"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific groups or teams

    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
    EH
    -0.82
     Synd
    -0.72
     Jere
    -0.71
    clone
    -0.67
    Ale
    -0.66
     Cros
    -0.65
     Cork
    -0.65
     Jol
    -0.64
    olkien
    -0.64
    Eth
    -0.64
    POSITIVE LOGITS
     Squad
    2.39
     attendant
    2.03
     attendants
    1.52
     Ops
    0.97
     rug
    0.87
     wagon
    0.87
    linger
    0.86
    ibi
    0.85
     popcorn
    0.84
    wagon
    0.83
    Activations Density 0.048%

    No Known Activations