© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 1860
    Prev
    Next
    INDEX
    Explanations

    places or locations that can host events or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or places for events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oad
    -0.85
    lean
    -0.79
    ned
    -0.68
    orers
    -0.67
    dri
    -0.63
    eping
    -0.62
    aks
    -0.61
    cycl
    -0.60
    gon
    -0.59
     pil
    -0.59
    POSITIVE LOGITS
     venue
    3.54
     venues
    2.48
     arena
    1.46
     stadium
    1.43
     organisers
    1.33
     promoter
    1.32
     ballpark
    1.29
    venue
    1.25
     forum
    1.24
     arenas
    1.23
    Activations Density 0.012%

    No Known Activations