© 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. 18530
    Prev
    Next
    INDEX
    Explanations

    proper nouns consisting of multiple words with an apostrophe included

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "O'" followed by a name or title

    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
    »Ĵ
    -0.85
    terday
    -0.77
     actionGroup
    -0.72
     eclipse
    -0.69
    isphere
    -0.67
    iae
    -0.66
     incent
    -0.66
     applicable
    -0.64
    OPLE
    -0.61
    nown
    -0.60
    POSITIVE LOGITS
    Brien
    1.36
    Neill
    1.35
    Connor
    1.31
    Donnell
    1.31
    Malley
    1.30
    Reilly
    1.22
    Leary
    1.22
    Neal
    1.16
    Neil
    1.14
    Connell
    1.14
    Activations Density 0.022%

    No Known Activations