© 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. 1-RES-JB
    11. 8899
    Prev
    Next
    INDEX
    Explanations

    various letters and symbols, potentially related to specific sources or organizations

    oai_token-act-pair · gpt-3.5-turbo

    identifiers or codes that resemble alphanumeric sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CLSID
    -0.60
     BaseType
    -0.59
     lasts
    -0.46
     referen
    -0.45
    inarily
    -0.45
     redistributed
    -0.44
    foreseen
    -0.43
     costs
    -0.43
     cost
    -0.43
    ividual
    -0.42
    POSITIVE LOGITS
    duc
    0.59
    uka
    0.53
    jee
    0.48
    etheless
    0.48
    cd
    0.46
    aks
    0.46
    zz
    0.46
    vt
    0.46
    lier
    0.46
    cel
    0.46
    Activations Density 2.010%

    No Known Activations