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. 2-RES-JB
    6. 22654
    Prev
    Next
    INDEX
    Explanations

    the word "how" preceded by another word

    oai_token-act-pair · gpt-3.5-turbo

    interrogative phrases and questions related to understanding or clarifying situations

    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
     tremend
    -0.86
     dime
    -0.82
     critical
    -0.74
     subjective
    -0.74
     subdiv
    -0.71
     hell
    -0.70
     chronically
    -0.69
     outl
    -0.69
     bureaucr
    -0.69
     altern
    -0.68
    POSITIVE LOGITS
    inite
    0.93
    ption
    0.93
    ius
    0.87
    enges
    0.85
    olean
    0.84
    atis
    0.84
    hess
    0.83
    stad
    0.83
    enh
    0.81
    enment
    0.79
    Activations Density 0.369%

    No Known Activations