© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 9435
    Prev
    Next
    INDEX
    Explanations

    information related to economic statistics and data

    oai_token-act-pair · gpt-3.5-turbo

    references to economic data related to wages and job growth

    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
    hai
    -0.64
    cil
    -0.61
     voic
    -0.60
     delicate
    -0.58
     distractions
    -0.58
     Brav
    -0.58
     quarantine
    -0.58
    inki
    -0.57
     frustrations
    -0.57
     urgently
    -0.57
    POSITIVE LOGITS
     since
    1.24
    since
    1.17
     contempor
    1.13
     averaged
    1.03
     1901
    1.00
     1973
    0.96
     1979
    0.96
     1951
    0.94
     1910
    0.92
     annually
    0.91
    Activations Density 0.583%

    No Known Activations