Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 13866
    Prev
    Next
    INDEX
    Explanations

    compound verbs and their related forms

    oai_token-act-pair · gpt-3.5-turbo

    grammatical elements, particularly verbs and nouns, along with discussions of their uses and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jri
    -0.87
    ONSORED
    -0.86
    psey
    -0.79
    Offline
    -0.75
    raphics
    -0.75
    clerosis
    -0.73
    adeon
    -0.72
     IPS
    -0.72
     Revelations
    -0.71
    cffff
    -0.70
    POSITIVE LOGITS
     pronouns
    1.11
    verb
    1.04
    ciation
    0.96
     verbs
    0.96
     verb
    0.94
     noun
    0.93
     suffix
    0.93
     pronoun
    0.92
     phrase
    0.86
     phrases
    0.84
    Activations Density 0.078%

    No Known Activations