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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 657
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find verbs associated with communication, organization, and facilitation

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements and discussions about necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opez
    -0.77
    monds
    -0.72
    alties
    -0.69
    ngth
    -0.67
    dies
    -0.67
    chev
    -0.63
     stripes
    -0.62
     selves
    -0.62
    riors
    -0.59
    strength
    -0.59
    POSITIVE LOGITS
     happening
    1.16
     happen
    0.99
     Happ
    0.78
     ado
    0.77
     occurring
    0.76
     unintentional
    0.73
     happens
    0.70
     SECTION
    0.70
     happened
    0.69
     achievable
    0.69
    Activations Density 0.198%

    No Known Activations