© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 3593
    Prev
    Next
    INDEX
    Explanations

    verbs in their base form

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "be" in various grammatical forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.78
     affordability
    -0.61
    ablishment
    -0.61
    oleon
    -0.60
     accommodation
    -0.60
     Ples
    -0.59
     Kurd
    -0.58
     Recession
    -0.57
     impossibility
    -0.57
     Selection
    -0.57
    POSITIVE LOGITS
    hemoth
    1.30
    heading
    1.23
    arers
    1.19
    ardless
    1.14
    acons
    1.13
    amed
    1.12
    ige
    1.11
    yond
    1.06
    ijing
    1.05
    aming
    1.03
    Activations Density 0.064%

    No Known Activations