© 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. 3-RES-JB
    11. 23574
    Prev
    Next
    INDEX
    Explanations

    adjectives describing strong emotions such as love, hate, and excitement

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate emotional reactions or responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     examiner
    -0.54
     continuum
    -0.49
    Solution
    -0.47
     Solution
    -0.46
     deed
    -0.45
     Worlds
    -0.45
     Kingdom
    -0.44
     solution
    -0.44
    hyde
    -0.44
     description
    -0.43
    POSITIVE LOGITS
    arily
    0.67
    ibly
    0.64
    iably
    0.63
    ounded
    0.63
    iously
    0.62
    atively
    0.61
    inged
    0.61
    astically
    0.61
    aunted
    0.60
    anned
    0.59
    Activations Density 0.831%

    No Known Activations