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. 4-RES-JB
    6. 12657
    Prev
    Next
    INDEX
    Explanations

    instances where the concept of retaining something is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "retain" and its variations in various contexts

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

    No Comments

    Negative Logits
    PsyNetMessage
    -0.69
    Reply
    -0.66
     Plaza
    -0.63
    gom
    -0.61
     Everywhere
    -0.60
    psc
    -0.60
    Never
    -0.60
     Diver
    -0.57
     Khe
    -0.57
    China
    -0.57
    POSITIVE LOGITS
     retain
    0.89
     veter
    0.86
     retained
    0.80
     intact
    0.78
    ively
    0.78
     retains
    0.77
    rets
    0.77
    ees
    0.76
     retaining
    0.76
    ancies
    0.76
    Activations Density 0.017%

    No Known Activations