© 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. 3-RES-JB
    11. 8926
    Prev
    Next
    INDEX
    Explanations

    specific terms related to news networks, especially CBS

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the CBS network

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arist
    -0.88
    haps
    -0.87
    yip
    -0.79
    antics
    -0.78
    agnar
    -0.77
    arial
    -0.76
    afort
    -0.75
    amping
    -0.72
    raint
    -0.71
    aced
    -0.71
    POSITIVE LOGITS
    IRO
    1.09
    CBS
    1.09
    NEWS
    1.05
    ONES
    0.98
    DAQ
    0.96
    NBC
    0.95
    LINE
    0.89
    CI
    0.87
    DF
    0.87
    EW
    0.85
    Activations Density 0.012%

    No Known Activations