© 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. 1634
    Prev
    Next
    INDEX
    Explanations

    terms related to attributing causes or reasons for events

    oai_token-act-pair · gpt-3.5-turbo

    references to human error and its implications

    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
    apest
    -0.94
    efer
    -0.93
    scribe
    -0.75
    ensable
    -0.75
    raf
    -0.73
    apixel
    -0.73
    代
    -0.72
    ura
    -0.70
    uma
    -0.70
    apolis
    -0.69
    POSITIVE LOGITS
     coincidence
    1.25
     factors
    0.96
     misunderstanding
    0.95
     inexper
    0.92
     sheer
    0.92
     negligence
    0.92
     intentional
    0.91
     jealousy
    0.90
     incompetence
    0.90
     mistaken
    0.88
    Activations Density 0.576%

    No Known Activations