© 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
    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. 11820
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives containing the word "more."

    oai_token-act-pair · gpt-3.5-turbo

    references to an increase or emphasis on quantity or significance

    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
    ESE
    -0.76
    imaru
    -0.74
     Shooter
    -0.66
    isa
    -0.66
    ICE
    -0.66
     Recording
    -0.66
     Release
    -0.64
     Station
    -0.64
    Factor
    -0.64
    ocobo
    -0.64
    POSITIVE LOGITS
     adventurous
    0.92
     affluent
    0.86
     esoteric
    0.85
     complicated
    0.85
     mundane
    0.84
     worrisome
    0.82
     expensive
    0.81
     populous
    0.81
    hest
    0.80
     sophisticated
    0.80
    Activations Density 0.037%

    No Known Activations