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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 1945
    Prev
    Next
    INDEX
    Explanations

    phrases related to managing subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to subscription and related actions or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     embryos
    -0.71
     shorth
    -0.68
     Adv
    -0.67
     hypot
    -0.66
     Norton
    -0.66
     rud
    -0.65
     maneuver
    -0.64
    etta
    -0.62
     dividends
    -0.62
     parity
    -0.61
    POSITIVE LOGITS
    scribe
    3.93
    scribed
    3.02
    scription
    2.82
    scrib
    1.77
    scape
    1.74
    sc
    1.38
    sid
    1.30
    script
    1.28
    scene
    1.23
    hibited
    1.18
    Activations Density 0.026%

    No Known Activations