© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 5175
    Prev
    Next
    INDEX
    Explanations

    words related to thunder and storms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Thunder" in various contexts, particularly relating to storms and the sports team

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utions
    -0.64
     âĸĪ
    -0.64
    >>>>>>>>
    -0.63
     Ichigo
    -0.61
    ++++
    -0.61
     Leia
    -0.60
     Huma
    -0.59
     violet
    -0.59
     Nico
    -0.59
     Fiat
    -0.57
    POSITIVE LOGITS
    stru
    1.02
    lake
    1.00
    storm
    0.92
    storms
    0.90
    bol
    0.85
    eful
    0.82
    birds
    0.79
    bird
    0.79
    efully
    0.78
    lord
    0.78
    Activations Density 0.067%

    No Known Activations