© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 4905
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives indicating size or scale

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of "bigger" in comparisons

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

    No Comments

    Negative Logits
    shire
    -0.94
    pta
    -0.72
    endant
    -0.70
    endants
    -0.70
    onso
    -0.68
    EVA
    -0.68
    ARA
    -0.68
     Examiner
    -0.66
    syn
    -0.66
    rw
    -0.65
    POSITIVE LOGITS
     than
    1.05
     Than
    0.98
    than
    0.89
     eleph
    0.88
     sized
    0.81
    picture
    0.79
    oted
    0.79
    izont
    0.78
     iceberg
    0.77
     scale
    0.76
    Activations Density 0.020%

    No Known Activations