© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 6860
    Prev
    Next
    INDEX
    Explanations

    mentions of people speaking in public settings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "speak" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aredevil
    -0.70
    xtap
    -0.67
    zed
    -0.66
    pping
    -0.66
    ======
    -0.66
    ocket
    -0.65
    =~
    -0.65
    ilts
    -0.64
    rawler
    -0.62
     storing
    -0.61
    POSITIVE LOGITS
     aloud
    0.93
     fluent
    0.88
     volumes
    0.87
     louder
    0.82
     spoken
    0.81
     frankly
    0.79
    voice
    0.76
     eloqu
    0.75
     Mandarin
    0.75
     candid
    0.74
    Activations Density 0.055%

    No Known Activations