© 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. 10-RES-JB
    11. 13659
    Prev
    Next
    INDEX
    Explanations

    companies or institutions related to finance and investigations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of financial institutions and companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rar
    -0.72
    actionDate
    -0.71
    arse
    -0.70
    olean
    -0.69
    åĬ
    -0.68
    ibilities
    -0.66
    arial
    -0.66
    bike
    -0.64
    onal
    -0.64
    åĤ
    -0.63
    POSITIVE LOGITS
     Ltd
    0.93
    's
    0.89
     Holdings
    0.88
     itself
    0.82
     Presents
    0.81
     LLC
    0.79
     employees
    0.78
     founder
    0.77
    ®,
    0.77
     circa
    0.76
    Activations Density 0.242%

    No Known Activations