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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12713
    Prev
    Next
    INDEX
    Explanations

    phrases related to roosters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cock" and its variants used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.72
    éĹĺ
    -0.71
    PsyNetMessage
    -0.69
     psychiat
    -0.66
     Palestin
    -0.65
     GOODMAN
    -0.65
     kcal
    -0.64
    è£ħ
    -0.64
     publicity
    -0.63
    VK
    -0.63
    POSITIVE LOGITS
    roach
    1.61
    pit
    1.20
    crow
    1.10
    tail
    1.09
    haw
    1.06
    mong
    1.00
    tails
    1.00
    pool
    0.96
    pots
    0.95
    hawk
    0.92
    Activations Density 0.015%

    No Known Activations