© 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. 3668
    Prev
    Next
    INDEX
    Explanations

    words related to challenges or obstacles

    oai_token-act-pair · gpt-3.5-turbo

    words related to obstacles and challenges

    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
    ;;;;;;;;
    -0.71
    orno
    -0.71
    iere
    -0.69
    enza
    -0.69
    email
    -0.68
    owicz
    -0.66
    ership
    -0.66
    ossier
    -0.65
    consider
    -0.65
    uming
    -0.64
    POSITIVE LOGITS
    opus
    0.94
    acles
    0.83
     Remastered
    0.78
    acle
    0.77
     ILCS
    0.75
    frog
    0.75
    apy
    0.71
    culus
    0.66
    fish
    0.66
    ambers
    0.66
    Activations Density 0.018%

    No Known Activations