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. 0-RES-JB
    6. 4272
    Prev
    Next
    INDEX
    Explanations

    terms related to supervision or control

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "supervision" and other related punctuation or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FIR
    -0.70
    estone
    -0.70
    cow
    -0.70
    LA
    -0.66
     Examiner
    -0.64
    affe
    -0.64
     polyg
    -0.63
     Array
    -0.63
    plex
    -0.63
    ulse
    -0.63
    POSITIVE LOGITS
    -,
    2.19
     supervision
    1.80
    -'
    1.68
    -)
    1.60
    -.
    1.54
    ctive
    0.96
     \'
    0.91
     dependence
    0.87
    arya
    0.87
     patronage
    0.87
    Activations Density 0.061%

    No Known Activations