Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 6725
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "shell"

    oai_token-act-pair · gpt-3.5-turbo

    references to "shell" and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įå
    -0.77
     Moody
    -0.70
     Gohan
    -0.64
    riad
    -0.64
     Scrib
    -0.62
    uana
    -0.60
     trave
    -0.59
    ————————————————
    -0.59
     Mub
    -0.58
    rences
    -0.58
    POSITIVE LOGITS
    fish
    1.28
    shock
    1.23
    shell
    1.07
     casing
    0.89
    bash
    0.88
    acked
    0.85
    brook
    0.85
    acking
    0.84
     shells
    0.82
     shell
    0.81
    Activations Density 0.072%

    No Known Activations