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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 9-RES-JB
    6. 11089
    Prev
    Next
    INDEX
    Explanations

    words related to changes or developments

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "have" and its variations indicating possession or existence

    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
     Penal
    -0.70
     territ
    -0.67
     Commun
    -0.66
     recalls
    -0.65
     Deliver
    -0.63
     hears
    -0.62
     observing
    -0.61
     possessing
    -0.60
     conceive
    -0.59
     juggling
    -0.59
    POSITIVE LOGITS
     risen
    1.40
     been
    1.39
     plummeted
    1.30
     become
    1.21
     soared
    1.20
     deteriorated
    1.19
     fallen
    1.19
    been
    1.17
     dwind
    1.16
     begun
    1.15
    Activations Density 0.147%

    No Known Activations