© 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. 2-RES-JB
    11. 23708
    Prev
    Next
    INDEX
    Explanations

    words related to causation or logical conclusions

    oai_token-act-pair · gpt-3.5-turbo

    the word "thus" and its various contexts of usage

    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
    ten
    -0.69
     Kl
    -0.65
     Children
    -0.60
     Polo
    -0.60
     Ones
    -0.59
     Scott
    -0.58
     Leather
    -0.58
     Lobby
    -0.58
     Food
    -0.57
    track
    -0.57
    POSITIVE LOGITS
    forth
    0.88
    bered
    0.81
    forward
    0.79
     convol
    0.79
    è£ħ
    0.77
    mia
    0.77
     misunder
    0.76
     guiActiveUn
    0.75
    ãĤ´ãĥ³
    0.75
     far
    0.74
    Activations Density 0.015%

    No Known Activations