© 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. 10-RES-JB
    11. 2883
    Prev
    Next
    INDEX
    Explanations

    indicators of statistical significance or critical results in a research context

    oai_token-act-pair · gpt-3.5-turbo

    topics related to research findings on relationships and social behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tune
    -0.78
     Collider
    -0.73
    Planet
    -0.72
    ãĥ¯ãĥ³
    -0.72
    Fuck
    -0.71
     Orche
    -0.70
    Ñı
    -0.69
     Tomorrow
    -0.68
    Alright
    -0.68
     Prepare
    -0.67
    POSITIVE LOGITS
     males
    1.10
     females
    1.04
     prevalence
    1.01
     whereas
    1.00
     incidence
    0.98
     adolescents
    0.98
     decreases
    0.98
     moreover
    0.97
     studies
    0.97
     interestingly
    0.96
    Activations Density 0.449%

    No Known Activations