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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 7378
    Prev
    Next
    INDEX
    Explanations

    words related to physical geographical features or medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to tides and tidal effects, particularly in a metaphorical or thematic context

    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
    raised
    -0.96
    enegger
    -0.92
    ioned
    -0.86
    raising
    -0.82
    orate
    -0.81
    oken
    -0.80
    ĸļ
    -0.78
    ronic
    -0.75
    elf
    -0.74
    skirts
    -0.72
    POSITIVE LOGITS
    idal
    1.10
    band
    0.74
     pend
    0.74
    ves
    0.67
    ITIES
    0.66
    ity
    0.66
     Veil
    0.65
    ãĥ¼ãĤ¯
    0.65
    ysis
    0.64
    ITY
    0.63
    Activations Density 0.016%

    No Known Activations