© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 7432
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a degree of certainty or confidence

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "at least in" indicating a subject's temporal or contextual constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uese
    -0.77
     therein
    -0.76
    killer
    -0.73
    Rum
    -0.65
    wine
    -0.65
    tre
    -0.63
     Abdul
    -0.62
    sworth
    -0.62
    NULL
    -0.58
     contag
    -0.58
    POSITIVE LOGITS
    roads
    1.04
     regards
    1.03
     conjunction
    0.97
     regard
    0.92
     spite
    0.91
    animate
    0.88
     hindsight
    0.84
     retrospect
    0.80
    organic
    0.80
     areas
    0.79
    Activations Density 0.084%

    No Known Activations