Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 20231
    Prev
    Next
    INDEX
    Explanations

    phrases related to making a significant impact or difference

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the impact of making a difference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yne
    -0.71
    rity
    -0.69
    milo
    -0.68
     diligently
    -0.67
    oleon
    -0.66
    ngth
    -0.64
    den
    -0.63
    acus
    -0.62
    lvl
    -0.61
    gression
    -0.61
    POSITIVE LOGITS
     difference
    1.82
     Difference
    1.40
     dent
    1.25
     impression
    1.16
     impact
    1.07
     ripple
    1.07
     mockery
    0.97
     sense
    0.97
     contribution
    0.93
     noticeable
    0.91
    Activations Density 0.097%

    No Known Activations