© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 20840
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the need to validate or demonstrate something through evidence or action

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "prove" and its variations

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

    No Comments

    Negative Logits
     newsletters
    -0.67
    letal
    -0.67
    alez
    -0.63
    atches
    -0.62
    ropri
    -0.61
    roman
    -0.60
    atched
    -0.59
     contrace
    -0.59
    atching
    -0.59
     liner
    -0.59
    POSITIVE LOGITS
    \\\\\\\\
    0.93
    ãĥ¼ãĥĨ
    0.83
    reader
    0.80
     proves
    0.76
    ||||
    0.75
    ãĤ¤ãĥĪ
    0.74
    ¯¯
    0.74
    rers
    0.72
    mount
    0.71
     prove
    0.70
    Activations Density 0.016%

    No Known Activations