© 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. 10-RES-JB
    11. 11089
    Prev
    Next
    INDEX
    Explanations

    locations within buildings

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or places

    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
     oneself
    -0.63
     yourselves
    -0.61
    annot
    -0.60
    anson
    -0.60
     backlash
    -0.59
    laus
    -0.58
    phabet
    -0.57
     IOC
    -0.56
     trending
    -0.56
     Kraft
    -0.56
    POSITIVE LOGITS
     overlooking
    0.92
    mates
    0.86
     balcony
    0.85
     apartment
    0.84
    mate
    0.84
     lair
    0.84
     doorstep
    0.84
    tips
    0.82
     porch
    0.80
     enclosure
    0.79
    Activations Density 0.132%

    No Known Activations