© 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. 10-RES-JB
    6. 12333
    Prev
    Next
    INDEX
    Explanations

    locations or places in different countries

    oai_token-act-pair · gpt-3.5-turbo

    mention of nationalities or geographic identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orians
    -0.74
    umers
    -0.70
     Saudis
    -0.68
    */(
    -0.67
    ril
    -0.65
    alist
    -0.64
     Germans
    -0.63
     Egyptians
    -0.63
     hairc
    -0.63
    finding
    -0.62
    POSITIVE LOGITS
     territory
    1.24
     countryside
    1.17
     shores
    1.12
     plains
    1.12
     border
    1.11
     territories
    1.09
     suburbs
    1.08
     airspace
    1.06
     suburb
    1.06
     borders
    1.04
    Activations Density 0.185%

    No Known Activations