© 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. 0-RES-JB
    11. 13847
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions or market data

    oai_token-act-pair · gpt-3.5-turbo

    unusual character sequences or non-standard symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reloaded
    -0.80
    ãĥ¼ãĥĨãĤ£
    -0.76
    TAIN
    -0.75
    anwhile
    -0.75
    ãĥ¼ãĥĨ
    -0.73
     McKenna
    -0.73
    rm
    -0.72
    vier
    -0.69
     Horowitz
    -0.66
    ãĥ³ãĤ¸
    -0.64
    POSITIVE LOGITS
    lesi
    0.69
    eas
    0.68
    rera
    0.66
    ractor
    0.65
     offic
    0.65
    sold
    0.63
    imet
    0.63
    ::
    0.62
    conv
    0.61
    orem
    0.59
    Activations Density 0.000%

    No Known Activations