© 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. 2-RES-JB
    11. 23087
    Prev
    Next
    INDEX
    Explanations

    adjectives or nouns related to perceptions and judgments

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "perceived" and its variations, indicating a focus on perceptions and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    annis
    -0.79
    trap
    -0.75
    kers
    -0.70
    hov
    -0.70
    hatt
    -0.68
    hire
    -0.67
    broken
    -0.66
    etsk
    -0.65
    spr
    -0.65
    cloth
    -0.65
    POSITIVE LOGITS
     perceptions
    0.85
    ãĥ³ãĤ¸
    0.82
    ãĤ¼
    0.81
    ãĥ¼ãĥĨ
    0.79
     unbeliev
    0.77
     unintention
    0.74
    éŃĶ
    0.73
     perceived
    0.73
     disson
    0.73
    Ô
    0.72
    Activations Density 0.013%

    No Known Activations