© 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. 4-RES-JB
    11. 4841
    Prev
    Next
    INDEX
    Explanations

    cone-related phrases or words

    oai_token-act-pair · gpt-3.5-turbo

    references to cones and their various contexts

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

    No Comments

    Negative Logits
    emb
    -0.80
    conscious
    -0.80
    ulators
    -0.80
    ulator
    -0.75
    ulative
    -0.72
    ulates
    -0.72
    oken
    -0.71
    ulated
    -0.69
     Feet
    -0.67
    athered
    -0.67
    POSITIVE LOGITS
     cone
    1.01
    xon
    0.97
     cones
    0.93
     Sentinel
    0.88
    utic
    0.82
     Canaveral
    0.75
    hower
    0.69
     Coul
    0.66
     slopes
    0.66
     applic
    0.66
    Activations Density 0.028%

    No Known Activations