© 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. 6-RES-JB
    11. 807
    Prev
    Next
    INDEX
    Explanations

    cities or locations

    oai_token-act-pair · gpt-3.5-turbo

    names of cities, countries, and associated geographical entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omever
    -0.71
    asonic
    -0.67
    igious
    -0.64
    risome
    -0.64
     Perkins
    -0.63
    fitted
    -0.61
    amsung
    -0.60
     mainland
    -0.60
    rag
    -0.59
    rical
    -0.58
    POSITIVE LOGITS
    sylv
    0.82
    ãģ®å®
    0.72
     ][
    0.68
     Edition
    0.66
     Intermediate
    0.65
    tarians
    0.62
    itiz
    0.61
     Metallic
    0.61
    Äĩ
    0.60
    */(
    0.60
    Activations Density 0.379%

    No Known Activations