© 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. 6-RES-JB
    11. 16904
    Prev
    Next
    INDEX
    Explanations

    words associated with counting or keeping track of something

    oai_token-act-pair · gpt-3.5-turbo

    references to tallying or counting events and instances

    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
     livest
    -0.69
     assail
    -0.62
    hov
    -0.62
     relations
    -0.62
     interrogation
    -0.62
     intervention
    -0.60
     interrog
    -0.59
     cultiv
    -0.59
    ©¶æ
    -0.59
    avage
    -0.59
    POSITIVE LOGITS
    enance
    0.81
    sung
    0.79
    ilus
    0.79
     tally
    0.78
    ming
    0.78
    alled
    0.77
     totals
    0.77
    sheet
    0.75
    STAT
    0.75
    ries
    0.74
    Activations Density 0.031%

    No Known Activations