© 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. 4-RES-JB
    11. 2701
    Prev
    Next
    INDEX
    Explanations

    locations and specific details within news articles

    oai_token-act-pair · gpt-3.5-turbo

    specific locations and associated details within a text

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

    No Comments

    Negative Logits
     fulfil
    -0.95
     realised
    -0.90
     whilst
    -0.82
    Firstly
    -0.80
     civilisation
    -0.80
     realise
    -0.79
     maths
    -0.78
     learnt
    -0.78
     flavour
    -0.77
     favour
    -0.77
    POSITIVE LOGITS
     statewide
    0.95
     Asheville
    0.92
    Alert
    0.88
     Boise
    0.84
     Downtown
    0.82
     downtown
    0.81
     Outdoor
    0.81
     COUNTY
    0.80
     Southwest
    0.80
     Wilmington
    0.80
    Activations Density 3.186%

    No Known Activations