© 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. 20555
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating position or location beneath something

    oai_token-act-pair · gpt-3.5-turbo

    words related to locations or objects positioned beneath something

    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
    QL
    -0.87
    olkien
    -0.80
    ACY
    -0.77
    videos
    -0.76
    76561
    -0.73
    yssey
    -0.71
    FF
    -0.69
    OB
    -0.69
    uden
    -0.68
    UFF
    -0.68
    POSITIVE LOGITS
     shoulders
    1.06
     horizon
    1.02
     cliffs
    0.97
     shoulder
    0.94
     layers
    0.94
     veil
    0.92
     railing
    0.89
     canopy
    0.87
     ribs
    0.85
     bushes
    0.85
    Activations Density 0.194%

    No Known Activations