© 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 EvalsExportsinterp-engineNEWAPI 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. 7-RES-JB
    11. 14617
    Prev
    Next
    INDEX
    Explanations

    inconclusive due to the lack of a consistent pattern in the activations for this neuron

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sembly
    -1.10
    undai
    -0.98
    eatures
    -0.97
    glomer
    -0.89
    ntil
    -0.87
     pse
    -0.86
    ebus
    -0.84
    abase
    -0.83
    ngth
    -0.82
    enhagen
    -0.81
    POSITIVE LOGITS
    ç
    1.51
    é
    1.50
    æ
    1.47
    åĪ
    1.42
    ãģ®
    1.41
    è
    1.40
    åŃIJ
    1.39
    å
    1.39
    é¾į
    1.39
    çĶ
    1.39
    Activations Density 0.043%

    No Known Activations