© 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. 11-RES-JB
    11. 6929
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "by" followed by multiple words

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "by" and phrases explaining actions or processes initiated by someone or something

    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
    ires
    -0.76
    glers
    -0.71
    ãĥĺ
    -0.68
    ustain
    -0.68
    RAW
    -0.68
    orate
    -0.66
    iral
    -0.66
    士
    -0.65
    oided
    -0.65
    Destroy
    -0.65
    POSITIVE LOGITS
     noting
    1.88
     stating
    1.80
     saying
    1.77
     describing
    1.77
     mentioning
    1.77
     praising
    1.74
     acknowledging
    1.73
     explaining
    1.73
     pointing
    1.72
     suggesting
    1.70
    Activations Density 0.314%

    No Known Activations