© 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. 11048
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or political discussions

    oai_token-act-pair · gpt-3.5-turbo

    punctuated phrases and clauses in sentences

    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
    osite
    -0.67
    chnology
    -0.64
    obos
    -0.61
    agen
    -0.60
     Ethernet
    -0.59
    Forge
    -0.58
    edge
    -0.57
     Bitcoins
    -0.57
    onomous
    -0.57
    eret
    -0.56
    POSITIVE LOGITS
     huh
    1.08
    âĢ
    1.06
    said
    1.02
     sir
    0.98
    »
    0.97
     eh
    0.95
    ``
    0.94
    \"
    0.94
     âĢ
    0.91
    "},
    0.88
    Activations Density 0.264%

    No Known Activations