© 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. 4-RES-JB
    11. 10556
    Prev
    Next
    INDEX
    Explanations

    phrases related to errors or mistakes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "error" and related terms

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

    No Comments

    Negative Logits
    apeake
    -0.83
    apy
    -0.82
    amen
    -0.81
    tsky
    -0.81
    electric
    -0.80
    nai
    -0.80
    bledon
    -0.78
    estine
    -0.78
    Electric
    -0.76
    APTER
    -0.71
    POSITIVE LOGITS
     error
    0.91
     guiActiveUn
    0.88
    gered
    0.87
     margin
    0.84
     errors
    0.84
    ously
    0.82
     dece
    0.79
     mishand
    0.78
     deceive
    0.77
     message
    0.74
    Activations Density 0.022%

    No Known Activations