© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 8114
    Prev
    Next
    INDEX
    Explanations

    words with characters not commonly found in the English language, such as special characters or non-standard letters

    oai_token-act-pair · gpt-3.5-turbo

    instances of formatting or styling artifacts in text, potentially indicating encoding issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glers
    -0.80
    gotten
    -0.74
    geries
    -0.72
    itars
    -0.71
     interf
    -0.70
    drawn
    -0.70
     decomp
    -0.69
    pired
    -0.68
    cheon
    -0.68
     similarity
    -0.67
    POSITIVE LOGITS
    į
    1.46
    £
    0.96
    à¤
    0.95
    Ø
    0.95
    ķ
    0.93
    ÑĤ
    0.92
    Į
    0.92
    °
    0.92
    ĩ
    0.90
    ħ
    0.90
    Activations Density 0.007%

    No Known Activations