© 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. 2-RES-JB
    11. 8369
    Prev
    Next
    INDEX
    Explanations

    references to a specific geographical location

    oai_token-act-pair · gpt-3.5-turbo

    terms related to locations, particularly focusing on places that share the name "adia" and historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     embryo
    -0.71
    imester
    -0.71
    umo
    -0.70
     transfers
    -0.67
    ench
    -0.63
     residue
    -0.63
     gauge
    -0.62
     shipment
    -0.62
    ologically
    -0.61
    ffield
    -0.61
    POSITIVE LOGITS
    heid
    0.94
    ħĭ
    0.85
    adia
    0.84
    ij士
    0.83
    Rog
    0.75
    plex
    0.75
    tainment
    0.74
     Yose
    0.74
    ¥µ
    0.73
    addons
    0.72
    Activations Density 0.023%

    No Known Activations