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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-RES-JB
    6. 425
    Prev
    Next
    INDEX
    Explanations

    the syllable "Bre" within words

    oai_token-act-pair · gpt-4-turbo

    locations or names related to "Bre" together with numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Bre" or related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iating
    -0.76
     Fired
    -0.73
    AGES
    -0.64
    ONES
    -0.64
     relief
    -0.63
     terr
    -0.62
    iated
    -0.62
    externalActionCode
    -0.61
     1862
    -0.61
    iates
    -0.60
    POSITIVE LOGITS
    thren
    1.13
    aks
    1.08
    akers
    1.07
    aker
    0.96
    aches
    0.96
    acher
    0.95
    Bre
    0.94
    eding
    0.94
    bre
    0.94
    achy
    0.91
    Activations Density 0.005%

    No Known Activations