© 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. 11-RES-JB
    11. 18652
    Prev
    Next
    INDEX
    Explanations

    words related to financial and economic concepts, as well as numerical values

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to economic conditions and alternative strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ricks
    -0.84
    aditional
    -0.83
    Nitrome
    -0.82
    ĸļ士
    -0.77
    ö
    -0.75
    ċ
    -0.75
    Ĝ
    -0.75
    Đ
    -0.75
    Ć
    -0.75
    À
    -0.75
    POSITIVE LOGITS
     year
    0.75
     place
    0.75
     country
    0.71
     period
    0.70
     situation
    0.69
     case
    0.68
     occasion
    0.68
     event
    0.67
     date
    0.66
     camp
    0.64
    Activations Density 0.127%

    No Known Activations