© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 10785
    Prev
    Next
    INDEX
    Explanations

    terms related to the company "GN" or variations thereof

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific organization or company

    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
    tes
    -0.70
    idas
    -0.69
    staking
    -0.68
    quer
    -0.68
     Gamble
    -0.68
     Wink
    -0.68
     Mour
    -0.67
     Ingram
    -0.66
     Wolver
    -0.65
     Russo
    -0.64
    POSITIVE LOGITS
    SS
    0.98
    ostic
    0.96
    OME
    0.93
    emonic
    0.89
    olor
    0.87
    ³
    0.86
    ostics
    0.85
    GN
    0.85
    ocide
    0.84
    esta
    0.82
    Activations Density 0.007%

    No Known Activations