© 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. 8-RES-JB
    11. 2476
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names or terms containing the sequence "der"

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the term "der."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sri
    -0.64
     eb
    -0.62
    zza
    -0.59
    eno
    -0.58
     cour
    -0.57
     Jian
    -0.57
     entr
    -0.56
     crim
    -0.55
     FTA
    -0.55
    enos
    -0.54
    POSITIVE LOGITS
    dash
    1.40
    minster
    0.98
    stocks
    0.96
    rama
    0.94
    theless
    0.93
    stood
    0.92
    lein
    0.92
    stand
    0.89
    wald
    0.88
    ocket
    0.87
    Activations Density 0.092%

    No Known Activations