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. 9-RES-JB
    6. 22542
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Tur" followed by a number (such as Tur9, Tur8)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Tur" and its variations, indicating a focus on the topic associated with that term

    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
     Known
    -0.65
     [&
    -0.64
    soDeliveryDate
    -0.63
    urance
    -0.63
     Safe
    -0.61
     Titanic
    -0.61
     guiActiveUnfocused
    -0.60
     largeDownload
    -0.60
     Integrity
    -0.59
     Superintendent
    -0.59
    POSITIVE LOGITS
    moil
    1.33
    kish
    1.26
    geon
    1.16
    ban
    1.12
    bul
    1.12
    fing
    1.11
    rible
    1.09
    rets
    1.09
    keys
    1.08
    bid
    1.07
    Activations Density 0.036%

    No Known Activations