© 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. 9-RES-JB
    11. 17231
    Prev
    Next
    INDEX
    Explanations

    phrases related to public events or discussions

    oai_token-act-pair · gpt-3.5-turbo

    events involving public or official gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uilt
    -0.74
     Genetic
    -0.69
     Growing
    -0.69
    forestation
    -0.68
    uably
    -0.67
    iasis
    -0.67
    inav
    -0.66
     Pwr
    -0.66
     eco
    -0.66
    oppable
    -0.65
    POSITIVE LOGITS
     adjourn
    1.34
     applause
    1.24
     microphone
    1.22
     podium
    1.22
     briefing
    1.16
     rehears
    1.16
     microphones
    1.14
     briefings
    1.14
     session
    1.13
     seated
    1.12
    Activations Density 1.286%

    No Known Activations