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. 7-RES-JB
    6. 6210
    Prev
    Next
    INDEX
    Explanations

    instances where the word "see" is used in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "see" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whistle
    -0.82
    inqu
    -0.69
    ÃŃa
    -0.66
    trap
    -0.64
     umbrella
    -0.64
    prime
    -0.63
    requisite
    -0.63
    fab
    -0.63
    Interstitial
    -0.60
    shaw
    -0.59
    POSITIVE LOGITS
    dust
    0.89
     how
    0.84
     firsthand
    0.79
     daylight
    0.76
     what
    0.68
    dogs
    0.67
     them
    0.67
    ilated
    0.66
    lights
    0.66
     visions
    0.65
    Activations Density 0.070%

    No Known Activations