© 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. 6-RES-JB
    11. 11652
    Prev
    Next
    INDEX
    Explanations

    mentions of news anchors or commentators

    oai_token-act-pair · gpt-3.5-turbo

    references to media personalities and news anchors

    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
     Corsair
    -0.69
    activation
    -0.67
    ogun
    -0.66
    TOR
    -0.65
    ahime
    -0.64
     Agric
    -0.64
    density
    -0.63
     1918
    -0.61
    venture
    -0.61
    depend
    -0.61
    POSITIVE LOGITS
     aired
    1.09
     Hannity
    1.08
     interviewer
    1.00
     Tonight
    0.98
    gyn
    0.95
     airing
    0.93
    CNN
    0.91
     anchor
    0.91
     broadcasts
    0.88
     listeners
    0.88
    Activations Density 0.101%

    No Known Activations