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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3626
    Prev
    Next
    INDEX
    Explanations

    mentions of cans

    oai_token-act-pair · gpt-3.5-turbo

    references to containers, particularly those used for food and beverages

    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
    RESULTS
    -0.73
     dishon
    -0.66
     privileged
    -0.63
     Advis
    -0.62
    ~~~~~~~~
    -0.62
     repayment
    -0.60
     striving
    -0.60
     Fighter
    -0.59
     Strikes
    -0.59
     wedd
    -0.59
    POSITIVE LOGITS
    vas
    1.18
    't
    1.15
    isters
    1.07
    berra
    1.05
    ister
    1.04
    adian
    0.99
    opy
    0.95
    atell
    0.94
    avan
    0.91
    ibal
    0.90
    Activations Density 0.051%

    No Known Activations