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. 8-RES-JB
    6. 21322
    Prev
    Next
    INDEX
    Explanations

    mentions of actions or activities involving physical presence or interaction with others

    oai_token-act-pair · gpt-3.5-turbo

    references to interpersonal interactions and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ukong
    -0.78
    ammy
    -0.74
    vous
    -0.69
    anty
    -0.69
    addons
    -0.66
    eries
    -0.65
     Rebell
    -0.63
    oi
    -0.63
     Syndrome
    -0.62
     Glover
    -0.62
    POSITIVE LOGITS
    aneously
    0.88
     instead
    0.85
     without
    0.81
    instead
    0.78
     rather
    0.76
     using
    0.76
     cheaply
    0.76
     manually
    0.72
    without
    0.71
     beforehand
    0.68
    Activations Density 0.352%

    No Known Activations