© 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. 11-RES-JB
    11. 22499
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "It" and related pronouns indicating a subject or focus in sentences

    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
     Flavoring
    -0.68
     Parables
    -0.65
    %%%%
    -0.61
    catentry
    -0.60
     ILCS
    -0.58
    Recent
    -0.55
     Principles
    -0.55
    oller
    -0.54
    anton
    -0.54
    ĵĺ
    -0.54
    POSITIVE LOGITS
     wasn
    1.44
     seemed
    1.38
     mattered
    1.36
     consisted
    1.34
     resembled
    1.28
     lasted
    1.28
     was
    1.27
     sounded
    1.26
     transpired
    1.25
     didn
    1.23
    Activations Density 0.174%

    No Known Activations