© 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. 10-RES-JB
    6. 8076
    Prev
    Next
    INDEX
    Explanations

    words related to movement back and forth, such as "forth," "swings," and "bouncing."

    oai_token-act-pair · gpt-3.5-turbo

    actions that involve movement or transitions between two points or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aceous
    -0.70
    ogi
    -0.67
    oir
    -0.67
    inn
    -0.65
    0100
    -0.65
    azo
    -0.64
    arton
    -0.63
    gz
    -0.61
    ge
    -0.60
    ora
    -0.60
    POSITIVE LOGITS
     depending
    1.06
    )=(
    0.89
     throughout
    0.89
     between
    0.87
     wildly
    0.85
    depending
    0.82
     smoothly
    0.81
     endlessly
    0.81
    ilaterally
    0.81
     unpredict
    0.81
    Activations Density 0.073%

    No Known Activations