© 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. 9-RES-JB
    11. 20730
    Prev
    Next
    INDEX
    Explanations

    specific entities or organizations related to lists or rankings

    oai_token-act-pair · gpt-3.5-turbo

    references to lists and rankings

    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
     irregularities
    -0.67
     apprehend
    -0.64
    erest
    -0.62
    resso
    -0.62
     noises
    -0.61
    zees
    -0.61
    oa
    -0.60
     prostitutes
    -0.59
     earnest
    -0.59
     interrupts
    -0.59
    POSITIVE LOGITS
     list
    1.99
    list
    1.57
     lists
    1.54
     roster
    1.41
     repertoire
    1.39
     checklist
    1.38
     LIST
    1.38
     Lists
    1.37
     List
    1.37
    LIST
    1.36
    Activations Density 0.964%

    No Known Activations