© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23353
    Prev
    Next
    INDEX
    Explanations

    the letter "x" followed by one or two specific numbers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'x' in various contexts, particularly in technical specifications or measurements

    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
    assetsadobe
    -0.89
     Seym
    -0.84
    ãĥĦ
    -0.80
    KEN
    -0.78
    awaru
    -0.76
    EMENT
    -0.75
    éĹĺ
    -0.75
    kamp
    -0.74
    blance
    -0.73
    姫
    -0.73
    POSITIVE LOGITS
    xxxxxxxx
    0.99
    posed
    0.98
    yz
    0.91
    avier
    0.90
     x
    0.90
    xxxx
    0.85
    iii
    0.85
    iang
    0.83
    xxx
    0.83
    xx
    0.82
    Activations Density 0.010%

    No Known Activations