© 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. 6-RES-JB
    11. 3685
    Prev
    Next
    INDEX
    Explanations

    season-related content or references

    oai_token-act-pair · gpt-3.5-turbo

    key concepts related to the seasons, emotional themes, and significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oros
    -0.71
    Joined
    -0.66
    gp
    -0.64
    imon
    -0.64
    DragonMagazine
    -0.62
    Associated
    -0.60
     guiActive
    -0.58
    king
    -0.58
    freedom
    -0.57
    urances
    -0.57
    POSITIVE LOGITS
     illustrates
    0.83
     exempl
    0.78
    adesh
    0.68
     underscores
    0.67
     Doodle
    0.66
     lacked
    0.65
     nonetheless
    0.65
     demonstrates
    0.64
     emphasizes
    0.64
     embodies
    0.63
    Activations Density 0.865%

    No Known Activations