© 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. 0-RES-JB
    11. 10032
    Prev
    Next
    INDEX
    Explanations

    words related to a specific location or structure named "Rot"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific locations or landmarks, particularly "Rot" and "Gat."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebted
    -0.78
    ilib
    -0.78
    ADRA
    -0.74
    hemer
    -0.70
     carbohyd
    -0.70
     narcissistic
    -0.70
     narciss
    -0.69
     sus
    -0.69
    eredith
    -0.69
    lyak
    -0.67
    POSITIVE LOGITS
     Rot
    2.82
     Gat
    2.20
    Rot
    1.98
     Ot
    1.53
     Til
    1.44
     Stras
    1.44
     Scot
    1.33
     Rut
    1.23
     Curt
    1.21
     Ort
    1.20
    Activations Density 0.062%

    No Known Activations