© 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. 7-RES-JB
    11. 23889
    Prev
    Next
    INDEX
    Explanations

    words related to actions that involve changing or transforming something

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "error"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kefeller
    -0.70
    IGHTS
    -0.69
    ership
    -0.68
    Premium
    -0.65
    ELS
    -0.64
    hips
    -0.64
     Spears
    -0.64
     supper
    -0.63
     Painter
    -0.63
    esville
    -0.62
    POSITIVE LOGITS
    asure
    1.28
    asures
    1.05
    rant
    1.00
    ogenous
    0.97
    icit
    0.94
    aser
    0.92
    rors
    0.91
    asing
    0.91
    got
    0.91
    mine
    0.91
    Activations Density 0.015%

    No Known Activations