© 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. 16951
    Prev
    Next
    INDEX
    Explanations

    dates and information about job positions and activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to professional roles and career details

    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
     Whilst
    -1.15
     whilst
    -1.14
    Firstly
    -1.01
     Firstly
    -0.93
     realise
    -0.88
    ´
    -0.86
    :-
    -0.85
     recognise
    -0.85
     realised
    -0.83
     analyse
    -0.82
    POSITIVE LOGITS
     Whitman
    0.91
     Cincinnati
    0.86
     nonprofit
    0.85
     Louisiana
    0.82
     Milwaukee
    0.82
     Hartford
    0.80
     Midwest
    0.80
     Wisconsin
    0.80
     Louisville
    0.80
     Washington
    0.80
    Activations Density 1.159%

    No Known Activations