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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 19525
    Prev
    Next
    INDEX
    Explanations

    phrases related to serving as a specific role or function

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "serves as" in various contexts indicating function or role

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osc
    -0.67
    romy
    -0.61
     Rebell
    -0.60
    uca
    -0.59
     Believe
    -0.58
    rone
    -0.58
    LINE
    -0.58
    oller
    -0.56
    Scope
    -0.56
    issue
    -0.56
    POSITIVE LOGITS
    criptions
    0.81
    pires
    0.79
     follows
    0.77
    pired
    0.77
     well
    0.74
     opposed
    0.72
     fodder
    0.72
     an
    0.71
     custod
    0.71
     integral
    0.71
    Activations Density 0.070%

    No Known Activations