© 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. 7-RES-JB
    11. 24027
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussing or interrogating the meaning or validity of statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to the meaning or substance of concepts

    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
    ener
    -0.77
    erella
    -0.72
    aceae
    -0.70
    arten
    -0.70
    aire
    -0.67
    isers
    -0.66
    iets
    -0.65
    forge
    -0.64
    frog
    -0.64
    way
    -0.63
    POSITIVE LOGITS
     hostilities
    0.86
     these
    0.85
     sentences
    0.81
     this
    0.78
     those
    0.76
     each
    0.74
     events
    0.72
     prayers
    0.71
     conversations
    0.69
     sentence
    0.68
    Activations Density 0.205%

    No Known Activations