© 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. 1-RES-JB
    11. 16047
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives related to size or magnitude

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "biggest" or largest entities or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isson
    -0.71
    bay
    -0.70
    endants
    -0.70
    icing
    -0.68
    ences
    -0.67
    heid
    -0.66
    syn
    -0.66
    CAP
    -0.66
    brid
    -0.66
     Therapy
    -0.65
    POSITIVE LOGITS
    gest
    1.03
     offender
    0.88
     culprit
    0.80
     unsolved
    0.78
     biggest
    0.78
     bang
    0.78
    iary
    0.76
     payoff
    0.76
     attraction
    0.74
     notor
    0.73
    Activations Density 0.014%

    No Known Activations