© 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. 14268
    Prev
    Next
    INDEX
    Explanations

    phrases indicating someone's feelings, thoughts, or intentions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms, indicating statements of existence or condition

    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
     Gap
    -0.63
    acly
    -0.63
     deform
    -0.63
     Fail
    -0.63
     unfocusedRange
    -0.62
     pile
    -0.61
    ãĥ¯
    -0.61
     mention
    -0.60
     culmin
    -0.59
     dynamics
    -0.59
    POSITIVE LOGITS
     glad
    1.21
     grateful
    1.12
     pleased
    1.07
     thankful
    1.05
     willing
    1.02
     ashamed
    0.99
     unaware
    0.99
     aware
    0.97
     thrilled
    0.95
     delighted
    0.94
    Activations Density 0.158%

    No Known Activations