© 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. 9-RES-JB
    11. 22661
    Prev
    Next
    INDEX
    Explanations

    time-related information such as dates, times, and financial figures

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and related financial data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     favorably
    -1.06
    colored
    -0.96
     unfavorable
    -0.95
    defense
    -0.95
     honoring
    -0.95
     canceled
    -0.91
     demeanor
    -0.90
    Defense
    -0.88
     utilized
    -0.87
     honored
    -0.87
    POSITIVE LOGITS
     programmes
    1.57
     £
    1.56
     organise
    1.55
     recognise
    1.54
     realise
    1.53
    £
    1.53
     civilisation
    1.53
     programme
    1.51
     maths
    1.50
     (£
    1.47
    Activations Density 1.527%

    No Known Activations