© 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. 6-RES-JB
    11. 12309
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages in a specific range

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and percentages related to statistics and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibaba
    -1.00
    uyomi
    -0.65
     Idle
    -0.64
    orno
    -0.64
    wait
    -0.61
     greets
    -0.60
     separat
    -0.60
    etsk
    -0.60
    itars
    -0.60
     havoc
    -0.59
    POSITIVE LOGITS
    dB
    0.76
     margin
    0.74
    umbers
    0.73
     mile
    0.68
     factor
    0.66
    factor
    0.66
    %.
    0.63
     virtue
    0.63
     margins
    0.62
     degrees
    0.61
    Activations Density 0.227%

    No Known Activations