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. 9-RES-JB
    6. 198
    Prev
    Next
    INDEX
    Explanations

    proper names starting with the letter "B" associated with various events, individuals, or places

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or names

    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
     constitu
    -0.71
    oslav
    -0.68
     unfocusedRange
    -0.60
     Nex
    -0.60
    rw
    -0.58
     insured
    -0.56
     Ern
    -0.55
     runes
    -0.55
     ratt
    -0.55
     resid
    -0.54
    POSITIVE LOGITS
    amina
    0.92
    atari
    0.76
    gui
    0.76
    anke
    0.74
    atis
    0.72
    etheus
    0.69
    î
    0.67
    artist
    0.66
    lehem
    0.66
    oya
    0.65
    Activations Density 0.063%

    No Known Activations