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. 7-RES-JB
    6. 15650
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical actions like throwing, tossing, knocking, etc

    oai_token-act-pair · gpt-3.5-turbo

    actions associated with throwing, cutting, or moving objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abama
    -0.68
    general
    -0.66
    EStreamFrame
    -0.64
     davidjl
    -0.62
     circumst
    -0.61
    Ô
    -0.60
    ËĪ
    -0.58
     Expend
    -0.58
     composing
    -0.57
    peak
    -0.57
    POSITIVE LOGITS
    ings
    1.53
    ers
    1.50
    ership
    1.43
    er
    1.30
    ners
    1.15
    ters
    1.14
    ingly
    1.11
    gers
    1.08
    ery
    1.06
    athon
    1.05
    Activations Density 0.225%

    No Known Activations