Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 23073
    Prev
    Next
    INDEX
    Explanations

    broadcast times for sports channels and mentions of specific programs

    oai_token-act-pair · gpt-3.5-turbo

    time references and scheduling information related to sports broadcasts

    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
    worthy
    -0.76
    worthiness
    -0.74
    igent
    -0.74
    abase
    -0.71
    ãĤ¼ãĤ¦ãĤ¹
    -0.70
    insured
    -0.68
    Shape
    -0.68
    itives
    -0.67
    ivated
    -0.66
    SPONSORED
    -0.66
    POSITIVE LOGITS
     TBD
    0.83
     airs
    0.76
     EST
    0.70
     noon
    0.68
     HOU
    0.68
     TBA
    0.68
     Pacific
    0.67
     cloudy
    0.66
     CST
    0.63
    ODE
    0.62
    Activations Density 0.080%

    No Known Activations