© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 3180
    Prev
    Next
    INDEX
    Explanations

    phrases related to vocal elements or dialogue

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "voice" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amily
    -0.75
    imes
    -0.70
    icol
    -0.69
    agher
    -0.68
    erenn
    -0.67
    etheless
    -0.65
    icip
    -0.64
    isc
    -0.63
    onday
    -0.62
    addy
    -0.62
    POSITIVE LOGITS
     recorder
    1.06
    voice
    0.91
    plays
    0.85
     voice
    0.85
     recordings
    0.84
    banks
    0.82
     spoken
    0.81
     chords
    0.81
     voices
    0.79
     cords
    0.78
    Activations Density 0.049%

    No Known Activations