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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 3372
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific acronym "BB"

    oai_token-act-pair · gpt-3.5-turbo

    references to "BB" 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
    izational
    -0.85
    bourg
    -0.84
    ional
    -0.81
    ources
    -0.81
    perse
    -0.79
    izations
    -0.76
    endez
    -0.76
    angered
    -0.74
    ainment
    -0.73
    pora
    -0.72
    POSITIVE LOGITS
    BB
    0.98
    zeb
    0.79
    ZZ
    0.77
    ATH
    0.76
    FW
    0.75
    ooth
    0.74
    INC
    0.73
    VO
    0.73
    ONY
    0.72
    iol
    0.71
    Activations Density 0.010%

    No Known Activations