© 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. 9302
    Prev
    Next
    INDEX
    Explanations

    phrases related to gathering and organizing information or data

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "compile."

    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
    phasis
    -0.83
    hal
    -0.78
    holes
    -0.75
    alle
    -0.71
    orthy
    -0.70
    alg
    -0.68
    aline
    -0.68
    arat
    -0.68
    phas
    -0.65
    thur
    -0.65
    POSITIVE LOGITS
     compiled
    1.28
     compiling
    0.93
     compilation
    0.90
    ãĤ¤ãĥĪ
    0.81
    ãĥ¼ãĥĨãĤ£
    0.73
    ãĥį
    0.73
    ãĤ¹ãĥĪ
    0.71
    LECT
    0.69
    åĪ
    0.68
    ãĥ¯
    0.68
    Activations Density 0.013%

    No Known Activations