© 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. 8-RES-JB
    11. 2703
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations, especially mountains and cities

    oai_token-act-pair · gpt-3.5-turbo

    names of places or geographical features

    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
    irlf
    -0.71
     Magnum
    -0.67
     Caf
    -0.65
    zsche
    -0.65
     Ending
    -0.65
     Tradition
    -0.62
    ÃŁ
    -0.61
     Das
    -0.60
     Parables
    -0.59
    icist
    -0.59
    POSITIVE LOGITS
    monds
    0.85
    pling
    0.75
     poles
    0.70
    igham
    0.68
    worthy
    0.65
    aleigh
    0.65
    enei
    0.63
    unic
    0.60
    alos
    0.59
    ngth
    0.59
    Activations Density 0.193%

    No Known Activations