© 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. 9133
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sequence of events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the pronoun 'she' in contexts of waking or becoming aware

    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
    Sharp
    -0.73
    ãĥIJ
    -0.69
     Engineers
    -0.69
    fleet
    -0.68
    ©¶æ¥µ
    -0.67
    behind
    -0.62
    dimension
    -0.61
    prov
    -0.60
    ä
    -0.59
    roman
    -0.58
    POSITIVE LOGITS
     arrived
    1.10
     finally
    1.05
     returned
    1.02
     awoke
    0.99
     regained
    0.98
     finished
    0.97
     reapp
    0.90
     reached
    0.90
     resumed
    0.88
     woke
    0.87
    Activations Density 0.165%

    No Known Activations