© 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. 0-RES-JB
    11. 14890
    Prev
    Next
    INDEX
    Explanations

    phrases related to renegades or rebels

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific word related to successful completion or finality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     instructions
    -0.66
     undecided
    -0.64
     satisfied
    -0.63
     workload
    -0.63
     PF
    -0.62
     similarities
    -0.61
     overweight
    -0.61
     supervision
    -0.61
     rumors
    -0.61
     unsure
    -0.60
    POSITIVE LOGITS
    ade
    4.56
    ades
    3.25
    ADE
    2.57
    aded
    2.34
    ading
    2.21
    ader
    1.80
    aders
    1.78
    asion
    1.49
    adia
    1.36
    ada
    1.34
    Activations Density 0.013%

    No Known Activations