© 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. 12995
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences starting with the word "generally"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating commonality or general trends

    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
    ÄŁ
    -0.86
     Billion
    -0.76
    hao
    -0.76
    vana
    -0.74
    lda
    -0.73
     Orchestra
    -0.72
    tein
    -0.71
    yle
    -0.71
    ters
    -0.68
    lez
    -0.68
    POSITIVE LOGITS
     regarded
    0.95
     exha
    0.92
     speaking
    0.90
    ensical
    0.85
     assumed
    0.84
     inclined
    0.82
     frowned
    0.82
     metic
    0.81
     confined
    0.81
     accepted
    0.81
    Activations Density 0.010%

    No Known Activations