© 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. 0-RES-JB
    11. 7545
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating a strong positive emotional connection or attachment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of fondness or affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CCC
    -0.80
     Signal
    -0.64
     IF
    -0.63
    upper
    -0.62
    medi
    -0.60
     Thomson
    -0.60
     procedural
    -0.60
     Wa
    -0.60
     Regulation
    -0.59
     Matth
    -0.59
    POSITIVE LOGITS
     fond
    3.95
     affection
    1.61
     nostalg
    1.44
     lov
    1.17
     penchant
    1.17
     nostalgic
    1.13
     liking
    1.09
     keen
    1.09
     proud
    1.07
     nostalgia
    1.06
    Activations Density 0.026%

    No Known Activations