© 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. 10-RES-JB
    11. 13895
    Prev
    Next
    INDEX
    Explanations

    technical terms or specialized methods used in various fields

    oai_token-act-pair · gpt-3.5-turbo

    references to various techniques

    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
    ãĥ©ãĥ³
    -0.70
    APTER
    -0.70
    engers
    -0.70
    watching
    -0.68
    endar
    -0.68
    onen
    -0.68
    riel
    -0.67
    oÄŁ
    -0.67
    isconsin
    -0.65
     Membership
    -0.64
    POSITIVE LOGITS
    ologies
    1.29
     employed
    1.16
     pioneered
    1.11
     techniques
    1.00
     utilized
    0.97
     used
    0.96
    kit
    0.95
     perfected
    0.91
     devised
    0.89
     methods
    0.86
    Activations Density 0.072%

    No Known Activations