Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 876
    Prev
    Next
    INDEX
    Explanations

    adjectives related to personality traits

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing events and their characteristics

    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
    eele
    -0.75
    govtrack
    -0.68
     pairs
    -0.64
    IELD
    -0.62
    etus
    -0.62
    ederation
    -0.61
     Dise
    -0.61
    renheit
    -0.61
    icts
    -0.61
    inite
    -0.60
    POSITIVE LOGITS
     minded
    0.95
     demeanor
    0.91
     nature
    0.80
     manner
    0.80
     upbringing
    0.77
     affair
    0.76
     spirited
    0.73
     approach
    0.70
     paced
    0.67
    istic
    0.67
    Activations Density 0.640%

    No Known Activations