© 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. 2304
    Prev
    Next
    INDEX
    Explanations

    references to storing and archiving data or information

    oai_token-act-pair · gpt-3.5-turbo

    references to storage and organization of information

    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
    yip
    -0.76
    ihad
    -0.69
    opoulos
    -0.68
    irection
    -0.67
    endon
    -0.66
    ocious
    -0.66
    idas
    -0.65
    ffect
    -0.65
    irez
    -0.63
    akedown
    -0.63
    POSITIVE LOGITS
     archives
    1.20
     drawer
    1.18
     freezer
    1.17
     folders
    1.16
     storage
    1.15
     archive
    1.11
     clipboard
    1.10
    storage
    1.09
     cabinets
    1.07
     folder
    1.06
    Activations Density 0.332%

    No Known Activations