© 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. 8-RES-JB
    11. 296
    Prev
    Next
    INDEX
    Explanations

    names or terms related to specific locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    repeated letters or sounds, indicating a focus on phonetic or alliterative qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStream
    -0.71
     familiar
    -0.66
     trough
    -0.65
     pac
    -0.64
     refrain
    -0.62
     audience
    -0.62
     synchronized
    -0.62
     explanatory
    -0.61
     referrals
    -0.60
     acqu
    -0.59
    POSITIVE LOGITS
    ornings
    0.96
    opsis
    0.96
    ake
    0.94
    ield
    0.82
    UFF
    0.82
    asons
    0.81
    akings
    0.81
    uff
    0.78
    iken
    0.76
    aru
    0.76
    Activations Density 0.211%

    No Known Activations