© 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. 2-RES-JB
    11. 2049
    Prev
    Next
    INDEX
    Explanations

    information related to sports, particularly players and events associated with the All-Star label

    oai_token-act-pair · gpt-3.5-turbo

    references to "All-Star" selections in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.93
     pse
    -0.75
    »Ĵ
    -0.73
     unintention
    -0.73
    ¿½
    -0.73
    choes
    -0.72
    ĵĺ
    -0.71
    Ń·
    -0.70
    anguage
    -0.69
    odcast
    -0.68
    POSITIVE LOGITS
    bucks
    1.10
    vation
    1.01
    Star
    0.89
    star
    0.87
    Ve
    0.86
    light
    0.85
    ring
    0.82
    rod
    0.79
    Moon
    0.79
    League
    0.79
    Activations Density 0.011%

    No Known Activations