© 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. 9-RES-JB
    11. 20813
    Prev
    Next
    INDEX
    Explanations

    instances of statements and opinions

    oai_token-act-pair · gpt-3.5-turbo

    affirmations or positive sentiments about collective efforts or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ¥µ
    -0.76
    ãĥ¥
    -0.73
     Miracle
    -0.72
     Gadget
    -0.69
    ĸļ
    -0.68
    Mech
    -0.68
    quick
    -0.66
     Maze
    -0.66
     maze
    -0.66
     miraculous
    -0.65
    POSITIVE LOGITS
     endorse
    1.45
     voted
    1.40
     oppose
    1.30
     opposes
    1.29
     vote
    1.29
     opposed
    1.27
     disagree
    1.25
     sympath
    1.24
     endorsed
    1.24
     endorsing
    1.19
    Activations Density 0.672%

    No Known Activations