© 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. 4-RES-JB
    11. 15195
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms related to different topics or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of existence

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

    No Comments

    Negative Logits
     shoulders
    -0.72
    reci
    -0.70
    med
    -0.66
    geon
    -0.66
    anche
    -0.65
    jer
    -0.64
    Magn
    -0.63
    verbs
    -0.62
    gar
    -0.62
    NetMessage
    -0.60
    POSITIVE LOGITS
    uality
    0.96
    ality
    0.87
    aeda
    0.86
     existence
    0.81
     Machina
    0.80
    entially
    0.79
    istence
    0.79
     Reincarn
    0.77
     incarn
    0.77
    entials
    0.77
    Activations Density 0.011%

    No Known Activations