© 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. 9-RES-JB
    11. 3600
    Prev
    Next
    INDEX
    Explanations

    descriptions of urban scenes involving actions and sounds typically associated with traffic and city life

    oai_token-act-pair · gpt-3.5-turbo

    elements related to urban life and its challenges

    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
    ãĤ´ãĥ³
    -0.85
    igen
    -0.84
    exempt
    -0.80
    itiz
    -0.75
    ilege
    -0.74
     Pwr
    -0.74
    redit
    -0.73
    ifestyle
    -0.73
    ogene
    -0.73
    ummer
    -0.72
    POSITIVE LOGITS
     balcon
    1.31
     rooft
    1.21
     passers
    1.18
     silhou
    1.15
     rows
    1.10
     roofs
    1.09
     shouts
    1.07
     sidewalks
    1.05
     screams
    1.02
     chests
    1.02
    Activations Density 0.423%

    No Known Activations