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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 4333
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sequential or temporal progression of events

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "have" in various tenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemThumbnailImage
    -0.71
    soType
    -0.68
    note
    -0.68
     note
    -0.61
    uty
    -0.60
     misuse
    -0.60
     relates
    -0.60
     hostage
    -0.60
     advoc
    -0.59
    isSpecialOrderable
    -0.58
    POSITIVE LOGITS
     finished
    1.29
     completed
    1.23
     gotten
    1.21
     risen
    1.14
     begun
    1.08
     exhausted
    1.07
     fallen
    1.07
     regained
    1.06
     gone
    1.06
     been
    1.06
    Activations Density 0.153%

    No Known Activations