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. 21669
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or situations that happened before or without certain circumstances

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating temporal circumstances or conditions preceding or following events

    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
    anon
    -0.68
     constitu
    -0.67
    IDER
    -0.67
    issance
    -0.67
    Rog
    -0.65
    ciation
    -0.64
    ALTH
    -0.64
    CTV
    -0.63
    Rum
    -0.63
    ugi
    -0.63
    POSITIVE LOGITS
     slightest
    0.90
     slight
    0.70
     watered
    0.69
    yip
    0.66
    ipolar
    0.65
     superficial
    0.64
    ividual
    0.64
    irlf
    0.59
    amic
    0.59
     embryonic
    0.59
    Activations Density 0.063%

    No Known Activations