© 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. 0-RES-JB
    11. 2900
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to specific geographical locations, particularly the state of Idaho and cities like Boise and Spokane

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the state of Idaho and related locations

    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
    oyer
    -0.81
     Ryder
    -0.80
     VS
    -0.79
    PM
    -0.76
     DR
    -0.76
     "$:/
    -0.75
     PS
    -0.75
     Pf
    -0.75
     Ryu
    -0.75
     pharmac
    -0.73
    POSITIVE LOGITS
     Idaho
    3.71
     Boise
    2.23
     Spokane
    1.78
    Utah
    1.53
     Tucson
    1.31
     Wichita
    1.31
     Fresno
    1.29
     Anchorage
    1.28
    aho
    1.28
     Montana
    1.27
    Activations Density 0.035%

    No Known Activations