© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 4491
    Prev
    Next
    INDEX
    Explanations

    instances where an outcome is described as a result of a preceding action or event

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "as a result."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    undai
    -0.76
     tradem
    -0.72
     bolted
    -0.68
     spaced
    -0.68
    cot
    -0.67
    bor
    -0.66
     millenn
    -0.65
     notor
    -0.64
     impe
    -0.64
    icrobial
    -0.63
    POSITIVE LOGITS
    iments
    0.85
    ivity
    0.83
     result
    0.81
    result
    0.79
    iveness
    0.77
     Result
    0.76
    iment
    0.76
    ively
    0.75
    Results
    0.73
    hess
    0.73
    Activations Density 0.029%

    No Known Activations