© 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. 15270
    Prev
    Next
    INDEX
    Explanations

    references to significant philosophers or theorists

    oai_token-act-pair · gpt-3.5-turbo

    references to influential philosophers and their concepts

    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
     Kodi
    -0.76
    Lago
    -0.75
     servicing
    -0.74
    venge
    -0.72
    AMI
    -0.72
    gallery
    -0.72
    LOAD
    -0.71
    ACTION
    -0.71
     lia
    -0.69
     Apex
    -0.68
    POSITIVE LOGITS
     philosophers
    1.22
     philosopher
    1.18
    icist
    1.12
    ocrates
    1.10
     Aristotle
    1.04
    zsche
    1.02
     scholars
    0.99
     theorists
    0.98
     theorem
    0.97
     mathematician
    0.96
    Activations Density 0.318%

    No Known Activations