© 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. 7604
    Prev
    Next
    INDEX
    Explanations

    phrases with a sense of urgency and direct instructions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal knowledge or persuasive appeals

    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
     Plaint
    -0.71
     Canaver
    -0.65
    RESULTS
    -0.65
    aucus
    -0.63
     Defendants
    -0.62
    :[
    -0.60
     '[
    -0.60
    OSP
    -0.60
     IPM
    -0.59
    ropri
    -0.58
    POSITIVE LOGITS
     kidding
    0.81
     ya
    0.79
     blah
    0.76
    !.
    0.73
    cha
    0.73
    !).
    0.72
    ?).
    0.71
     math
    0.69
     maths
    0.67
     gotta
    0.67
    Activations Density 0.545%

    No Known Activations