© 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. 3-RES-JB
    11. 12931
    Prev
    Next
    INDEX
    Explanations

    timestamps in the format hours:minutes

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly colons and their frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dinand
    -0.91
    ĸļ
    -0.86
    avorite
    -0.76
    rette
    -0.72
     behav
    -0.70
     behavi
    -0.67
    ocious
    -0.66
    ourge
    -0.66
    icultural
    -0.64
     tremend
    -0.63
    POSITIVE LOGITS
    59
    1.06
    58
    1.01
    53
    1.00
    57
    0.99
    00
    0.98
    51
    0.94
    56
    0.94
    54
    0.93
    05
    0.91
    5000
    0.90
    Activations Density 0.116%

    No Known Activations