© 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. 16738
    Prev
    Next
    INDEX
    Explanations

    prepositions and pronouns followed by certain nouns or phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possession or association

    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
    Champ
    -0.80
    ãĤ¼ãĤ¦ãĤ¹
    -0.74
    TEXT
    -0.70
    govtrack
    -0.69
    pedia
    -0.65
    à¦
    -0.63
    Sport
    -0.63
     crore
    -0.61
    cham
    -0.60
    IQ
    -0.60
    POSITIVE LOGITS
     course
    0.86
     relations
    0.74
     sorts
    0.70
     wanting
    0.70
     the
    0.69
    elia
    0.68
     his
    0.68
     aspiring
    0.68
     those
    0.67
    raltar
    0.64
    Activations Density 0.056%

    No Known Activations