© 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. 10-RES-JB
    11. 24365
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of 'twin'

    oai_token-act-pair · gpt-3.5-turbo

    references to twins or twin-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.78
    UME
    -0.77
     CoC
    -0.76
    Interstitial
    -0.74
    icz
    -0.73
    miah
    -0.70
    stract
    -0.68
    ibaba
    -0.67
    UTE
    -0.66
    ãģĵ
    -0.65
    POSITIVE LOGITS
    ned
    1.30
    ning
    1.23
     Peaks
    0.99
     towers
    0.96
     peaks
    0.88
    fold
    0.87
     brother
    0.85
    osaurs
    0.85
     Towers
    0.83
    nings
    0.81
    Activations Density 0.025%

    No Known Activations