© 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. 3-RES-JB
    11. 22978
    Prev
    Next
    INDEX
    Explanations

    mentions of decomposition or disintegration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to decomposition and disintegration processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chie
    -0.72
    bara
    -0.68
    bey
    -0.66
    Recomm
    -0.66
     amen
    -0.66
    Resp
    -0.65
    reon
    -0.65
    ellation
    -0.64
    ror
    -0.62
     Direction
    -0.61
    POSITIVE LOGITS
     toilets
    0.71
    ibles
    0.70
     remnants
    0.65
    river
    0.64
     pits
    0.63
     scars
    0.63
     sickness
    0.63
    frog
    0.63
     spores
    0.61
    »Ĵ
    0.61
    Activations Density 0.126%

    No Known Activations