© 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. 14515
    Prev
    Next
    INDEX
    Explanations

    mentions of specific scenarios or instances of something in documents

    oai_token-act-pair · gpt-3.5-turbo

    references to specific instances or occurrences of events

    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
    roe
    -0.72
    obil
    -0.71
     streng
    -0.71
     livest
    -0.69
    redit
    -0.65
    owered
    -0.65
    ACTED
    -0.64
    rica
    -0.64
    rote
    -0.64
    pez
    -0.63
    POSITIVE LOGITS
    cases
    1.35
     cases
    1.21
    case
    0.91
     Cases
    0.90
     instances
    0.89
    backs
    0.77
    paces
    0.77
    rooms
    0.76
     Case
    0.75
     Canaver
    0.74
    Activations Density 0.013%

    No Known Activations