© 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. 3620
    Prev
    Next
    INDEX
    Explanations

    strings containing both letters and numbers

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to TV show schedules and 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
    hement
    -0.73
     destro
    -0.72
    ophen
    -0.72
     painting
    -0.70
     understatement
    -0.65
     manoeuv
    -0.65
     adulthood
    -0.63
     sovere
    -0.62
     doub
    -0.62
     ethanol
    -0.62
    POSITIVE LOGITS
    Below
    0.96
    Spoiler
    0.88
    ------------------------
    0.85
    ccording
    0.85
    ":[{"
    0.83
    earances
    0.81
    Links
    0.80
    Language
    0.78
    Rank
    0.78
     Links
    0.77
    Activations Density 0.215%

    No Known Activations