© 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. 4-RES-JB
    11. 7580
    Prev
    Next
    INDEX
    Explanations

    mentions of obtaining or acquiring something

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "get your hands on."

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

    No Comments

    Negative Logits
    ļéĨĴ
    -0.70
     Prediction
    -0.68
    ICO
    -0.62
     Savings
    -0.62
    Marginal
    -0.62
     RAND
    -0.60
     Corrections
    -0.60
     1942
    -0.60
    actionDate
    -0.59
     Sec
    -0.59
    POSITIVE LOGITS
    pring
    1.18
    maid
    1.12
    handed
    0.98
    chool
    0.95
    creen
    0.93
    ingers
    0.93
    hander
    0.88
     paws
    0.86
    shake
    0.84
    bag
    0.84
    Activations Density 0.019%

    No Known Activations