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. 3-RES-JB
    6. 21398
    Prev
    Next
    INDEX
    Explanations

    words related to collaborations and partnerships

    oai_token-act-pair · gpt-3.5-turbo

    references to collaborative efforts or partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vex
    -0.78
     Compass
    -0.74
     Grimes
    -0.70
    HCR
    -0.68
     AVG
    -0.67
     Dickinson
    -0.67
     DRAG
    -0.66
    FontSize
    -0.63
    ¥µ
    -0.62
     cancell
    -0.61
    POSITIVE LOGITS
    talk
    1.11
    sized
    1.02
    interstitial
    0.96
    ranking
    0.95
    produced
    0.93
    release
    0.93
    management
    0.93
    branded
    0.92
    government
    0.92
    signed
    0.91
    Activations Density 0.059%

    No Known Activations