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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 3687
    Prev
    Next
    INDEX
    Explanations

    locations and landmarks

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and names of cities or regions

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

    No Comments

    Negative Logits
    apego
    -0.58
    oaded
    -0.57
    acebook
    -0.55
    inyl
    -0.50
    milo
    -0.49
    rehensive
    -0.49
    uilt
    -0.48
    ļé
    -0.47
    inx
    -0.46
    Tags
    -0.45
    POSITIVE LOGITS
     circles
    0.61
     vicinity
    0.61
     guise
    0.61
     nutshell
    0.57
     area
    0.55
     countryside
    0.54
     cavern
    0.53
     courtyard
    0.53
     precincts
    0.51
     hurry
    0.50
    Activations Density 1.289%

    No Known Activations