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. 4-RES-JB
    6. 23655
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data packets and network communication

    oai_token-act-pair · gpt-3.5-turbo

    terms related to data packets and networking concepts

    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
     Democr
    -0.81
    shire
    -0.78
    avid
    -0.68
    Rated
    -0.66
     Galile
    -0.65
    aft
    -0.63
     perpetual
    -0.61
    pert
    -0.59
     Aram
    -0.58
     trending
    -0.58
    POSITIVE LOGITS
     packets
    1.04
     packet
    1.01
    eers
    0.80
    folios
    0.76
    nown
    0.74
    ãĥ¥
    0.73
     Contents
    0.72
    aging
    0.72
    ulent
    0.69
    meal
    0.69
    Activations Density 0.007%

    No Known Activations