© 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. 9970
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences starting with "The way"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a manner or perspective of doing something

    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
    usters
    -0.83
    oppable
    -0.77
    igh
    -0.75
    emies
    -0.72
    ĸļ
    -0.72
    oubtedly
    -0.69
    ãĤĴ
    -0.68
    usting
    -0.68
    ighed
    -0.67
    thouse
    -0.66
    POSITIVE LOGITS
    ward
    1.03
     things
    0.98
     forward
    0.94
     they
    0.87
    forward
    0.82
    fare
    0.81
     we
    0.77
    points
    0.77
     Forward
    0.76
     Europeans
    0.76
    Activations Density 0.045%

    No Known Activations