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. 3048
    Prev
    Next
    INDEX
    Explanations

    phrases expressing certainty or knowledge

    oai_token-act-pair · gpt-3.5-turbo

    expressions of knowing or awareness related to various situations

    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
    SPONSORED
    -0.72
    udo
    -0.70
    cour
    -0.68
    enture
    -0.63
     territ
    -0.62
     certific
    -0.62
    unia
    -0.62
    BuyableInstoreAndOnline
    -0.62
    udeau
    -0.62
     seiz
    -0.61
    POSITIVE LOGITS
    )</
    0.71
     sarc
    0.67
    PLA
    0.61
     Mean
    0.61
     lied
    0.58
     Slip
    0.58
    )=
    0.58
    !'"
    0.56
     true
    0.55
    ujah
    0.55
    Activations Density 0.424%

    No Known Activations