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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 18455
    Prev
    Next
    INDEX
    Explanations

    locations, including cities, states, and countries

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HMS
    -0.64
     Boko
    -0.59
     interviewer
    -0.58
    itness
    -0.57
     Mermaid
    -0.57
    çĶ°
    -0.55
     Doodle
    -0.54
    anchez
    -0.53
    xit
    -0.53
    CVE
    -0.53
    POSITIVE LOGITS
     besides
    0.94
    heastern
    0.87
    region
    0.78
     region
    0.77
    ;;;;;;;;;;;;
    0.77
     Region
    0.76
    heast
    0.75
    ibaba
    0.72
    outheastern
    0.72
    ozo
    0.72
    Activations Density 0.443%

    No Known Activations