© 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. 4-RES-JB
    11. 4379
    Prev
    Next
    INDEX
    Explanations

    situations where something could be improved or changed

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases expressing opinions or suggestions about improvement

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

    No Comments

    Negative Logits
    plus
    -0.72
    lines
    -0.60
     sclerosis
    -0.59
    bound
    -0.59
    rowd
    -0.58
    metadata
    -0.58
    ching
    -0.57
    ritical
    -0.56
     unexplained
    -0.56
     cleared
    -0.56
    POSITIVE LOGITS
    yip
    0.81
     Adviser
    0.73
    hower
    0.68
    mpeg
    0.64
     Seym
    0.63
    osate
    0.62
     Advisor
    0.62
    amation
    0.60
    amph
    0.60
    ibur
    0.59
    Activations Density 0.425%

    No Known Activations