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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 21001
    Prev
    Next
    INDEX
    Explanations

    instances of the word "speak"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "speak."

    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
    aredevil
    -0.82
    ======
    -0.71
    \/\/
    -0.69
    ikhail
    -0.64
    awaru
    -0.64
    gart
    -0.63
    xon
    -0.63
    rawler
    -0.62
    ishers
    -0.62
    ritional
    -0.62
    POSITIVE LOGITS
     aloud
    1.02
    voice
    0.91
     volumes
    0.89
     louder
    0.89
     voices
    0.84
     spoken
    0.83
     fluent
    0.82
     loudly
    0.80
     english
    0.77
    ofer
    0.77
    Activations Density 0.046%

    No Known Activations