© 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. 23398
    Prev
    Next
    INDEX
    Explanations

    years in the format 'YYYY' that are prominent in a text

    oai_token-act-pair · gpt-3.5-turbo

    mention of specific years

    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
    letes
    -0.72
    hing
    -0.62
    tro
    -0.59
    ype
    -0.57
    hed
    -0.56
     VIDEOS
    -0.56
    hop
    -0.55
    Liter
    -0.55
     phosphate
    -0.54
     bip
    -0.54
    POSITIVE LOGITS
    ruary
    0.79
    assetsadobe
    0.77
    foundland
    0.74
    furt
    0.74
     onwards
    0.69
    inson
    0.67
    -'
    0.66
    ynski
    0.65
     Heights
    0.65
     2010
    0.65
    Activations Density 0.296%

    No Known Activations