© 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. 3-RES-JB
    11. 8745
    Prev
    Next
    INDEX
    Explanations

    mentions of persons holding the position of "chair" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to positions of leadership or authority

    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
     IMAGES
    -0.76
    090
    -0.68
    Sharp
    -0.62
     DATA
    -0.61
    DEF
    -0.61
     intercepted
    -0.61
     Partnership
    -0.61
    ogue
    -0.60
     Mile
    -0.58
    uder
    -0.58
    POSITIVE LOGITS
     chair
    1.29
    lift
    1.17
    chair
    1.16
     Chair
    1.14
    chairs
    1.08
    woman
    1.07
     chairs
    1.03
    person
    1.02
    holder
    0.97
    Chair
    0.92
    Activations Density 0.010%

    No Known Activations