© 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. 6-RES-JB
    6. 2753
    Prev
    Next
    INDEX
    Explanations

    information related to televised broadcasts of events and match schedules

    oai_token-act-pair · gpt-3.5-turbo

    details about televised sports events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndra
    -1.10
     volunt
    -0.88
     modelling
    -0.83
    ework
    -0.81
    zsche
    -0.77
    amous
    -0.76
    aez
    -0.76
    milo
    -0.76
    alling
    -0.76
     pose
    -0.76
    POSITIVE LOGITS
     ESPN
    1.22
     broadcasts
    1.12
     HBO
    1.07
     Broadcasting
    1.06
    ESPN
    1.06
     broadcast
    1.05
    Tickets
    1.04
     Sports
    1.03
     broadcasters
    1.01
     telev
    1.01
    Activations Density 0.543%

    No Known Activations