© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 4305
    Prev
    Next
    INDEX
    Explanations

    locations or directions

    oai_token-act-pair · gpt-3.5-turbo

    geographical directional terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipedia
    -0.88
    ocrates
    -0.88
    thood
    -0.87
    OPA
    -0.79
    artisan
    -0.72
    wagen
    -0.72
    ISA
    -0.72
    LER
    -0.71
    Sharp
    -0.71
    osponsors
    -0.71
    POSITIVE LOGITS
    most
    1.39
     portion
    1.27
     side
    1.16
     periphery
    1.11
     hemisphere
    1.11
     outskirts
    1.10
     edge
    1.08
     end
    1.07
     region
    1.06
     corner
    1.06
    Activations Density 0.085%

    No Known Activations