© 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. 8775
    Prev
    Next
    INDEX
    Explanations

    phrases related to questioning and evaluating others' actions or intentions

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their relationships to assessments or evaluations

    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
    classic
    -0.71
    ellen
    -0.71
    complete
    -0.69
    icable
    -0.63
     unanimous
    -0.62
    Ultra
    -0.61
     Achievements
    -0.61
    nette
    -0.60
    canon
    -0.60
    anship
    -0.59
    POSITIVE LOGITS
     intended
    0.75
     stimuli
    0.73
     attacked
    0.73
     alleged
    0.73
    umbn
    0.72
     depicted
    0.71
     referenced
    0.70
     targeted
    0.70
     allegedly
    0.69
     employed
    0.66
    Activations Density 0.478%

    No Known Activations