© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 9381
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names in a news or article-like context

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and their related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pwr
    -0.78
    ulhu
    -0.78
     Mehran
    -0.74
    Prev
    -0.73
    assium
    -0.73
    byss
    -0.71
    ËĪ
    -0.71
    »Ĵ
    -0.70
    amed
    -0.70
     Tradable
    -0.69
    POSITIVE LOGITS
     remarks
    1.54
     assertion
    1.48
     comments
    1.39
     characterization
    1.38
     assertions
    1.38
     statement
    1.37
     remark
    1.34
     reasoning
    1.27
     statements
    1.25
     contention
    1.24
    Activations Density 0.230%

    No Known Activations