© 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. 14503
    Prev
    Next
    INDEX
    Explanations

    names or terms containing the sequence "Dob" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    names of people and notable entities

    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
    Angelo
    -0.71
     Torrent
    -0.71
    terday
    -0.68
    alam
    -0.67
    CHO
    -0.66
     Hook
    -0.65
     Sass
    -0.65
     delinquent
    -0.62
     Intermediate
    -0.61
     Caller
    -0.61
    POSITIVE LOGITS
    bing
    1.40
    riet
    1.12
    nob
    1.11
    lique
    1.11
    bled
    1.10
    bons
    1.09
    acterial
    1.09
    rien
    1.08
    oard
    1.04
    blers
    1.04
    Activations Density 0.020%

    No Known Activations