© 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. 6-RES-JB
    11. 13769
    Prev
    Next
    INDEX
    Explanations

    terms related to the broader or wider context or setting

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating a broad or wide perspective

    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
    girls
    -0.81
    boy
    -0.77
    _-
    -0.76
    LV
    -0.72
    girl
    -0.72
     Drawn
    -0.70
    liest
    -0.69
    Guard
    -0.67
    Lex
    -0.67
    rol
    -0.67
    POSITIVE LOGITS
     societal
    1.00
     spectrum
    0.93
     than
    0.90
    soType
    0.89
     ado
    0.87
     context
    0.81
     reperto
    0.81
     entreprene
    0.79
     circulation
    0.79
     organis
    0.79
    Activations Density 0.027%

    No Known Activations