© 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. 3-RES-JB
    6. 6515
    Prev
    Next
    INDEX
    Explanations

    instances of the word "voiced" or related terms indicating expression or communication of opinions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "voice" or related verbs that indicate expressing opinions or concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illard
    -0.78
    ney
    -0.74
    neys
    -0.70
     Journals
    -0.64
    rug
    -0.64
    igm
    -0.63
    addy
    -0.63
    idem
    -0.63
    oner
    -0.63
     Profit
    -0.62
    POSITIVE LOGITS
     voiced
    1.05
     voicing
    0.92
     voices
    0.92
     voic
    0.89
    unci
    0.88
     voice
    0.87
     chords
    0.86
     vocal
    0.85
    DonaldTrump
    0.77
     vocals
    0.76
    Activations Density 0.009%

    No Known Activations