© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 2911
    Prev
    Next
    INDEX
    Explanations

    words related to questions or inquiries

    oai_token-act-pair · gpt-3.5-turbo

    word forms related to 'idate' and 'idation' processes, likely in the context of status or assessments

    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
     spilling
    -0.73
     rag
    -0.67
    cow
    -0.65
     lav
    -0.64
     covenant
    -0.64
    zl
    -0.64
     mesh
    -0.61
     staples
    -0.61
     accord
    -0.60
     Firefly
    -0.59
    POSITIVE LOGITS
    idates
    4.51
    idate
    4.50
    idation
    2.99
    idated
    2.69
    idity
    1.15
    id
    1.11
    uana
    1.11
    imura
    1.10
    idon
    1.04
    ide
    1.00
    Activations Density 0.018%

    No Known Activations