© 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. 6-RES-JB
    11. 20472
    Prev
    Next
    INDEX
    Explanations

    phrases indicating differing perspectives or opinions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "differently."

    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
    ELY
    -0.71
    urance
    -0.68
    raltar
    -0.67
    stay
    -0.64
    uster
    -0.64
    ories
    -0.63
     necessity
    -0.62
    ãĥİ
    -0.62
    anon
    -0.61
    URES
    -0.61
    POSITIVE LOGITS
     situated
    1.08
     behaved
    0.93
     inclined
    0.89
     disposed
    0.88
     minded
    0.86
     tuned
    0.85
     equipped
    0.82
     tailored
    0.80
     Tradable
    0.76
     shaped
    0.76
    Activations Density 0.024%

    No Known Activations