© 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. 11073
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, especially "Dawkins" and "Parsons"

    oai_token-act-pair · gpt-3.5-turbo

    the names of prominent individuals, particularly Richard Dawkins and Chandler Parsons

    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
    ting
    -0.70
     Manit
    -0.68
     Scotia
    -0.67
     joint
    -0.67
     Breaker
    -0.66
    å§
    -0.58
     acquisitions
    -0.57
    attled
    -0.57
     diagnosis
    -0.57
     subtitle
    -0.57
    POSITIVE LOGITS
    pread
    1.00
    alez
    0.96
     Dawkins
    0.92
    ource
    0.90
    cliffe
    0.89
    cale
    0.88
    ilon
    0.88
    linger
    0.86
    aeda
    0.84
    rss
    0.84
    Activations Density 0.022%

    No Known Activations