© 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. 10-RES-JB
    11. 13765
    Prev
    Next
    INDEX
    Explanations

    emotional reactions or opinions expressed in written text

    oai_token-act-pair · gpt-3.5-turbo

    expressions of disappointment or dissatisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mirage
    -0.65
     pyramid
    -0.62
     accomp
    -0.62
     shadow
    -0.61
     specialist
    -0.61
     crus
    -0.60
     Camel
    -0.60
     Amon
    -0.59
     presumed
    -0.59
     trainer
    -0.59
    POSITIVE LOGITS
    onto
    1.01
    ï¸ı
    0.99
    ationally
    0.95
    gently
    0.94
    him
    0.93
    efe
    0.89
    against
    0.89
    early
    0.87
    selves
    0.85
    oward
    0.84
    Activations Density 0.243%

    No Known Activations