© 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. 1-RES-JB
    11. 3544
    Prev
    Next
    INDEX
    Explanations

    mentions of direct messages (DMs) with specific numbers representing varying degrees of relevance to the neuron

    oai_token-act-pair · gpt-3.5-turbo

    references to digital media or data management concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itals
    -0.71
    raltar
    -0.68
    ĸļ
    -0.66
     behalf
    -0.66
     Niagara
    -0.66
    atchewan
    -0.65
     Sabres
    -0.65
    Īè
    -0.64
    Prev
    -0.64
     Tradable
    -0.63
    POSITIVE LOGITS
    DM
    1.11
     DM
    1.11
    MC
    0.82
     resil
    0.78
    NM
    0.73
    NF
    0.72
    ERG
    0.72
    ND
    0.71
    aign
    0.70
    ball
    0.68
    Activations Density 0.006%

    No Known Activations