Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 19476
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, specifically canyons and Mesa, Arizona

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geographical locations, particularly canyons

    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
    SN
    -0.70
     su
    -0.67
     TF
    -0.67
     analys
    -0.66
     deter
    -0.65
    rik
    -0.64
     ts
    -0.61
     favourable
    -0.60
     labou
    -0.60
    employed
    -0.60
    POSITIVE LOGITS
     Canyon
    4.06
     canyon
    2.16
    anyon
    1.66
     Mesa
    1.55
     Creek
    1.44
     Cove
    1.33
     Yosemite
    1.33
     Ranch
    1.32
     Cavern
    1.24
     Valley
    1.23
    Activations Density 0.014%

    No Known Activations