© 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. 0-RES-JB
    11. 10171
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or items related to maintenance or repair, particularly with a focus on physical objects

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word 'ups' and similar variations related to situations and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cloak
    -0.62
     literal
    -0.62
     hel
    -0.61
     Concord
    -0.59
     Lect
    -0.59
     Scotland
    -0.57
     clay
    -0.57
    otive
    -0.56
     direct
    -0.56
     disguise
    -0.56
    POSITIVE LOGITS
    ups
    4.16
    up
    2.44
     ups
    2.13
    downs
    1.92
    UP
    1.88
     Ups
    1.69
    offs
    1.53
    outs
    1.43
    Up
    1.42
    upp
    1.37
    Activations Density 0.013%

    No Known Activations