© 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. 7-RES-JB
    11. 2085
    Prev
    Next
    INDEX
    Explanations

    adjectives that express strong emotions like surprise or concern

    oai_token-act-pair · gpt-3.5-turbo

    terms expressing surprise or concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    resp
    -0.72
    agine
    -0.66
    elf
    -0.65
    ournal
    -0.65
    vous
    -0.65
    ighth
    -0.61
    aper
    -0.60
    cipl
    -0.59
    bey
    -0.59
    ravings
    -0.58
    POSITIVE LOGITS
     enough
    1.07
    LY
    0.98
     nonetheless
    0.93
    ly
    0.86
    ingly
    0.82
     because
    0.77
     considering
    0.75
     insofar
    0.75
     JPM
    0.73
    200000
    0.69
    Activations Density 0.184%

    No Known Activations