© 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. 6-RES-JB
    11. 4240
    Prev
    Next
    INDEX
    Explanations

    references to various types of objects, conditions, or actions that can be seen as extraordinary or extreme

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical conditions and problematic situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Inqu
    -0.57
    aples
    -0.55
    cept
    -0.53
    ells
    -0.51
     Sche
    -0.50
     Roose
    -0.50
     Nath
    -0.50
    pine
    -0.50
    alted
    -0.48
    hemat
    -0.47
    POSITIVE LOGITS
    .(
    0.81
     whilst
    0.81
    ./
    0.80
     respectively
    0.77
    *.
    0.74
    .''.
    0.72
    .
    0.70
    !.
    0.70
     (£
    0.70
     whenever
    0.68
    Activations Density 0.569%

    No Known Activations