© 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. 2902
    Prev
    Next
    INDEX
    Explanations

    words related to cardboard or materials associated with cardboard construction

    oai_token-act-pair · gpt-3.5-turbo

    references to cardboard

    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
    ivari
    -0.73
    ppard
    -0.72
    oren
    -0.69
    IFA
    -0.68
    nings
    -0.66
    ivot
    -0.65
    awar
    -0.65
    encers
    -0.64
    ioch
    -0.64
    alez
    -0.64
    POSITIVE LOGITS
     cardboard
    1.21
     boxes
    1.09
     box
    0.94
     BOX
    0.90
     coffin
    0.87
     wra
    0.84
     wrapper
    0.83
    ©¶æ¥µ
    0.82
     tubes
    0.80
    erton
    0.78
    Activations Density 0.006%

    No Known Activations