© 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. 0-RES-JB
    11. 7851
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Voice"

    oai_token-act-pair · gpt-3.5-turbo

    instances of "Voice" and its variations, indicating a focus on topics related to voice and representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crate
    -0.70
     drying
    -0.70
     mortg
    -0.66
    bons
    -0.65
    buck
    -0.65
     fres
    -0.64
     bun
    -0.63
    iche
    -0.63
     spend
    -0.63
     barley
    -0.63
    POSITIVE LOGITS
     Voice
    4.09
    Voice
    2.93
    voice
    2.42
     Voices
    2.18
     voice
    2.17
     voices
    1.62
     VO
    1.53
    Vo
    1.42
     Vo
    1.37
     voic
    1.35
    Activations Density 0.010%

    No Known Activations