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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 12682
    Prev
    Next
    INDEX
    Explanations

    mentions of something unspecified but important or significant in the context

    oai_token-act-pair · gpt-3.5-turbo

    references to vague or unspecified entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jad
    -0.64
    itative
    -0.59
    cent
    -0.58
    PC
    -0.57
    alde
    -0.57
    ort
    -0.56
    encing
    -0.56
    net
    -0.56
     Nation
    -0.55
    umb
    -0.55
    POSITIVE LOGITS
     something
    3.22
    something
    2.51
     somet
    2.30
     Something
    2.05
    Something
    1.97
     anything
    1.71
     somebody
    1.67
     someone
    1.60
    someone
    1.51
    anything
    1.50
    Activations Density 0.041%

    No Known Activations