© 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. 3548
    Prev
    Next
    INDEX
    Explanations

    phrases related to hidden or unexpected conditions or restrictions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "catch" in various contexts

    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
     sclerosis
    -0.79
    uilt
    -0.75
    unts
    -0.74
    arten
    -0.73
    ppard
    -0.71
    ovych
    -0.70
    htar
    -0.68
    urred
    -0.68
    uras
    -0.65
    olas
    -0.64
    POSITIVE LOGITS
    phrase
    1.22
    aways
    0.92
    backs
    0.84
     Catch
    0.78
    mong
    0.75
    weight
    0.74
    amac
    0.73
    ables
    0.72
    doors
    0.72
    bowl
    0.71
    Activations Density 0.022%

    No Known Activations