© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 9488
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions of throwing or discarding

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "toss" and its variations

    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
     Cer
    -0.74
     Calais
    -0.69
    eur
    -0.68
     Swedish
    -0.68
    external
    -0.68
     organisation
    -0.67
     Ac
    -0.66
    thel
    -0.64
     Fem
    -0.64
     Ec
    -0.63
    POSITIVE LOGITS
     toss
    3.72
     tossing
    2.36
     tossed
    2.28
     flips
    1.47
     flipping
    1.22
     flip
    1.18
     throw
    1.15
     chuck
    1.13
     flipped
    1.11
     Throw
    1.01
    Activations Density 0.035%

    No Known Activations