© 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. 2-RES-JB
    11. 21033
    Prev
    Next
    INDEX
    Explanations

    numerical values with a specific pattern, possibly related to a code or data format

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly ones that appear frequently like "69"

    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
    ition
    -0.75
    igent
    -0.72
    ingham
    -0.71
    pled
    -0.70
    iment
    -0.69
    alties
    -0.68
    igators
    -0.68
    itable
    -0.68
    fman
    -0.67
    aple
    -0.67
    POSITIVE LOGITS
    09
    1.00
    059
    0.96
    07
    0.94
    08
    0.93
    05
    0.92
    089
    0.91
    06
    0.90
    04
    0.89
    090
    0.87
    03
    0.86
    Activations Density 0.046%

    No Known Activations