© 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. 18681
    Prev
    Next
    INDEX
    Explanations

    words related to technical or mechanical issues and abnormalities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to malfunctions and abnormalities

    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
    è£ħ
    -0.87
    md
    -0.83
     Passage
    -0.81
    adr
    -0.79
    ighth
    -0.78
    ographies
    -0.74
     Partnership
    -0.73
    ovember
    -0.72
    âĺħâĺħ
    -0.71
    dden
    -0.70
    POSITIVE LOGITS
     malfunction
    1.00
     abnormal
    0.92
     uncontroll
    0.90
     aber
    0.87
     abnorm
    0.87
     disturbances
    0.82
     glitches
    0.81
     fluct
    0.80
     irregularities
    0.74
     impair
    0.74
    Activations Density 0.030%

    No Known Activations