© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7287
    Prev
    Next
    INDEX
    Explanations

    legislation or actions that are being taken or could be taken

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest open-ended possibilities or conditions

    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
    ahime
    -0.86
    uers
    -0.71
    lled
    -0.70
    ernels
    -0.69
    enhagen
    -0.66
    stadt
    -0.66
    ilies
    -0.65
    ãĥ¥
    -0.64
    multi
    -0.63
    xt
    -0.60
    POSITIVE LOGITS
     whatsoever
    1.49
     imaginable
    1.28
    soever
    1.08
     conceivable
    0.97
     slightest
    0.91
    pires
    0.90
     EVER
    0.88
     ever
    0.82
     hereafter
    0.81
     anywhere
    0.80
    Activations Density 0.482%

    No Known Activations