© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 20241
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal reflections and opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong emotions and reactions

    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
    catentry
    -0.81
    senal
    -0.66
     spam
    -0.65
     boosting
    -0.63
    ikarp
    -0.63
    cific
    -0.62
    maxwell
    -0.61
     OG
    -0.61
     carbohyd
    -0.60
     keyword
    -0.60
    POSITIVE LOGITS
    ,—
    1.04
    ;
    0.90
    .—
    0.85
     lest
    0.80
    enance
    0.79
    ankind
    0.79
     truths
    0.78
    enment
    0.78
    !
    0.77
    ––
    0.76
    Activations Density 0.513%

    No Known Activations