© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13765
    Prev
    Next
    INDEX
    Explanations

    adjectives describing deep or intense impact or change

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "profound" in various contexts

    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
    ©¶æ
    -0.88
    rera
    -0.73
    swick
    -0.72
    matched
    -0.70
    hops
    -0.70
    TAG
    -0.67
    phis
    -0.67
    resp
    -0.67
    igslist
    -0.65
    peak
    -0.65
    POSITIVE LOGITS
    ly
    0.84
     sadness
    0.80
     impact
    0.79
     philosophical
    0.77
     effect
    0.76
    est
    0.75
     sorrow
    0.74
     awe
    0.72
     affect
    0.70
    ness
    0.70
    Activations Density 0.031%

    No Known Activations