© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 11725
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or strategies that involve changing or impacting a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest potential solutions or opportunities for improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proud
    -0.68
     certific
    -0.67
     foregoing
    -0.64
     wary
    -0.64
     accustomed
    -0.61
     defect
    -0.60
     compliant
    -0.60
     proficient
    -0.60
     interested
    -0.59
     contag
    -0.58
    POSITIVE LOGITS
    \\\\\\\\
    0.89
     namely
    0.75
    ovie
    0.74
    maxwell
    0.73
    EStream
    0.70
     Corpus
    0.69
     Qualcomm
    0.69
    unin
    0.68
    ::::
    0.67
     Warlock
    0.65
    Activations Density 0.540%

    No Known Activations