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. 5500
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographical locations or people's origins

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas and brackets

    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
    aukee
    -0.77
    iners
    -0.76
    arettes
    -0.75
     IST
    -0.66
    Interstitial
    -0.65
     entrepreneurship
    -0.64
    ateurs
    -0.64
     manufact
    -0.63
     CoC
    -0.63
    ecided
    -0.62
    POSITIVE LOGITS
    note
    1.19
    ...]
    1.18
    Pg
    1.16
     citation
    1.01
    src
    1.00
    â̦]
    1.00
    ?]
    0.93
    Footnote
    0.92
    sic
    0.83
    ËĪ
    0.83
    Activations Density 0.038%

    No Known Activations