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. 8-RES-JB
    6. 18862
    Prev
    Next
    INDEX
    Explanations

    phrases related to collective action and making progress together toward a common goal

    oai_token-act-pair · gpt-3.5-turbo

    phrases conveying collective action or collaboration towards a common goal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Weird
    -0.73
     sampled
    -0.71
     curs
    -0.70
    anamo
    -0.64
    raph
    -0.63
    oval
    -0.59
    asma
    -0.59
     Bare
    -0.58
     slang
    -0.57
     Cock
    -0.57
    POSITIVE LOGITS
     prosper
    1.02
     someday
    1.00
     achieve
    0.98
     ultimately
    0.97
     achieving
    0.95
     propel
    0.95
     improve
    0.93
     eventually
    0.92
     prosperity
    0.92
     sustainable
    0.92
    Activations Density 0.668%

    No Known Activations