© 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. 7-RES-JB
    11. 22959
    Prev
    Next
    INDEX
    Explanations

    adjectives and nouns related to evaluation and impact

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the presence of significant or varying impacts or effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bis
    -0.71
    cakes
    -0.67
    ATS
    -0.67
     Posts
    -0.65
    hooting
    -0.63
    bet
    -0.62
    owship
    -0.62
     consulted
    -0.62
    anners
    -0.61
    bolt
    -0.61
    POSITIVE LOGITS
     implications
    0.98
     resonance
    0.98
     tendency
    0.96
     ripple
    0.95
     significance
    0.94
     ramifications
    0.92
     impact
    0.92
     reperc
    0.92
     effect
    0.90
     credibility
    0.89
    Activations Density 0.329%

    No Known Activations