© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 15055
    Prev
    Next
    INDEX
    Explanations

    locations or places within a community

    oai_token-act-pair · gpt-3.5-turbo

    place names, specifically geographic locations

    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
    ionic
    -0.77
    OST
    -0.71
    ially
    -0.68
    ographed
    -0.68
    Putin
    -0.67
    efully
    -0.67
    binary
    -0.66
    usted
    -0.66
    ubuntu
    -0.65
    igel
    -0.65
    POSITIVE LOGITS
     Resort
    1.32
     Ranch
    1.26
     Cemetery
    1.26
     Farms
    1.19
     Lodge
    1.16
     Parkway
    1.16
     Mall
    1.15
     Speedway
    1.14
     Village
    1.14
     Rd
    1.12
    Activations Density 0.168%

    No Known Activations