© 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. 15347
    Prev
    Next
    INDEX
    Explanations

    words related to the term "ink"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Dink" in various contexts

    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
    ccording
    -0.83
    ãĥ£
    -0.78
    ppa
    -0.75
     earthqu
    -0.73
     Âł Âł Âł Âł Âł Âł Âł Âł
    -0.70
    Þ
    -0.69
     Âł Âł Âł Âł
    -0.69
     compr
    -0.69
    blance
    -0.68
    è¦ļéĨĴ
    -0.66
    POSITIVE LOGITS
    erman
    0.98
    edin
    0.93
    enstein
    0.90
    ishly
    0.87
    iang
    0.85
    ners
    0.84
    ie
    0.82
    ery
    0.82
    ering
    0.81
    ers
    0.81
    Activations Density 0.010%

    No Known Activations