© 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. 7809
    Prev
    Next
    INDEX
    Explanations

    statistical data and demographic information

    oai_token-act-pair · gpt-3.5-turbo

    demographic and age-related statistics

    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
     Artemis
    -0.84
    CVE
    -0.74
    repair
    -0.69
    hack
    -0.69
     rigging
    -0.67
     sabotage
    -0.66
     scal
    -0.66
     sabot
    -0.64
    jam
    -0.63
     havoc
    -0.63
    POSITIVE LOGITS
     households
    1.20
    married
    1.19
    Hispanic
    1.18
     respondents
    1.17
     Married
    1.14
     married
    1.08
     unmarried
    1.08
     Hispanic
    1.05
     Household
    1.05
     Hispanics
    1.04
    Activations Density 0.345%

    No Known Activations