© 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. 9-RES-JB
    11. 2599
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by phrases indicating comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a frequency or prevalence of occurrences, particularly with the word "on."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RED
    -0.64
    Ñĭ
    -0.64
    Protect
    -0.62
    rament
    -0.60
     Defender
    -0.58
    ãĤĤ
    -0.56
    reet
    -0.56
    letter
    -0.55
    mins
    -0.54
     Bomb
    -0.53
    POSITIVE LOGITS
     occasion
    1.15
    etime
    1.14
    erous
    1.10
     occasions
    1.09
     behalf
    1.09
     average
    1.07
    eday
    1.04
    eness
    1.00
    shore
    1.00
     steroids
    0.97
    Activations Density 0.177%

    No Known Activations