© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7343
    Prev
    Next
    INDEX
    Explanations

    phrases related to identifying issues or challenges

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "the problem with"

    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
    ãĤ¼ãĤ¦ãĤ¹
    -0.95
    orah
    -0.77
    oult
    -0.76
    illion
    -0.71
    soon
    -0.71
    nis
    -0.70
    ograp
    -0.69
    ãģ®éŃĶ
    -0.66
    fab
    -0.65
    UME
    -0.65
    POSITIVE LOGITS
     regards
    1.24
     regard
    1.17
     respect
    0.92
    stood
    0.87
     impunity
    0.86
    draw
    0.81
     prejudice
    0.76
    standing
    0.74
     legality
    0.67
     dignity
    0.66
    Activations Density 0.067%

    No Known Activations