© 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. 16048
    Prev
    Next
    INDEX
    Explanations

    image captions with copyright information

    oai_token-act-pair · gpt-3.5-turbo

    image captions in the text

    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
    nex
    -0.75
     fortun
    -0.70
    ASE
    -0.66
    amin
    -0.66
    ced
    -0.64
     clutch
    -0.64
    nesia
    -0.63
     sed
    -0.63
     favor
    -0.63
     dice
    -0.62
    POSITIVE LOGITS
     caption
    0.99
     Annotations
    0.98
    acters
    0.91
     Murd
    0.81
     Quentin
    0.80
    edin
    0.79
     Damien
    0.72
     Fiona
    0.72
    ounters
    0.72
    atchewan
    0.71
    Activations Density 0.008%

    No Known Activations