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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 21184
    Prev
    Next
    INDEX
    Explanations

    references to actions or processes related to carrying out or implementing something, potentially with a connotation of finality or efficiency

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of execution

    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
    ijn
    -0.73
     Tire
    -0.68
    este
    -0.65
     Soda
    -0.64
     Lank
    -0.63
     Lanka
    -0.62
    Fi
    -0.61
    cott
    -0.60
     Fol
    -0.60
    aspberry
    -0.59
    POSITIVE LOGITS
     execute
    0.90
     executes
    0.87
     execution
    0.84
    eering
    0.82
     executing
    0.82
    sequence
    0.81
     executed
    0.80
    locks
    0.79
    ution
    0.77
     executions
    0.77
    Activations Density 0.034%

    No Known Activations