© 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. 22750
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rather" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rather" and its variations, suggesting a focus on expressions of preference or degrees of consideration

    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
    adium
    -0.90
    amba
    -0.89
    illary
    -0.80
    elsen
    -0.79
    azon
    -0.74
    arent
    -0.70
    uay
    -0.70
    ividual
    -0.69
    ocaust
    -0.68
    clud
    -0.68
    POSITIVE LOGITS
     amusing
    0.78
     tame
    0.77
     than
    0.72
     inconvenient
    0.72
     pathetic
    0.70
     innocuous
    0.70
     straightforward
    0.69
     Osw
    0.69
     harmless
    0.67
     benign
    0.67
    Activations Density 0.017%

    No Known Activations