Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 12363
    Prev
    Next
    INDEX
    Explanations

    mentions of sports activities and achievements

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to movement or progression in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cius
    -0.73
    essa
    -0.66
     Mub
    -0.60
    eers
    -0.60
    *)
    -0.59
    Parents
    -0.58
    comments
    -0.58
     lifes
    -0.57
     Pastebin
    -0.57
     Us
    -0.56
    POSITIVE LOGITS
     undrafted
    1.00
     into
    0.89
     undefeated
    0.86
    verning
    0.79
     ahead
    0.79
     downhill
    0.78
     unbeaten
    0.78
     bye
    0.76
     through
    0.75
    vt
    0.75
    Activations Density 0.088%

    No Known Activations