© 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. 7-RES-JB
    11. 15694
    Prev
    Next
    INDEX
    Explanations

    words related to reversals or actions involving reversing something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reverse processes or engineering

    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
    Interstitial
    -1.01
    lished
    -0.98
    chens
    -0.77
    utical
    -0.77
    uay
    -0.74
    akov
    -0.73
    urated
    -0.73
    thening
    -0.71
    riers
    -0.71
    liam
    -0.71
    POSITIVE LOGITS
     chronological
    0.96
    actively
    0.83
     engineer
    0.79
     symmetry
    0.73
     reverse
    0.73
    balanced
    0.73
     halves
    0.72
     engineered
    0.72
    wash
    0.71
    intuitive
    0.70
    Activations Density 0.023%

    No Known Activations