© 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. 24413
    Prev
    Next
    INDEX
    Explanations

    sentences mentioning various conditions or rules

    oai_token-act-pair · gpt-3.5-turbo

    references to various conditions, typically in a social, economic, or environmental context

    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
    sonian
    -1.03
    ilus
    -0.82
    umbn
    -0.82
    yright
    -0.74
    enic
    -0.68
    ãĤ¨ãĥ«
    -0.68
    lish
    -0.68
    ramid
    -0.68
     Huff
    -0.67
    adesh
    -0.67
    POSITIVE LOGITS
     conditions
    1.14
     Conditions
    1.00
     conducive
    0.89
     deterior
    0.86
     deteriorated
    0.86
     worsened
    0.85
    pring
    0.85
     condition
    0.80
     quo
    0.77
     conditioned
    0.76
    Activations Density 0.020%

    No Known Activations