© 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. 0-RES-JB
    11. 22353
    Prev
    Next
    INDEX
    Explanations

    keywords indicating something that is mandatory or necessary to comply with, often in legal or regulatory contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to obligations or necessities

    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
    lance
    -0.71
     Thoughts
    -0.66
    hester
    -0.66
    terson
    -0.64
    nah
    -0.64
    oho
    -0.63
    gom
    -0.63
    gang
    -0.62
    atters
    -0.62
    rand
    -0.61
    POSITIVE LOGITS
     required
    3.50
    required
    2.56
     needed
    2.31
     Required
    2.27
     necessary
    2.19
     requisite
    1.86
    Required
    1.86
     requirement
    1.85
    needed
    1.73
     mandated
    1.71
    Activations Density 0.015%

    No Known Activations