© 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. 8-RES-JB
    11. 18435
    Prev
    Next
    INDEX
    Explanations

    Keywords related to technical issues and criticisms, specifically related to software or hardware problems

    oai_token-act-pair · gpt-3.5-turbo

    expressions of impossibility or difficulty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ratulations
    -0.81
    reetings
    -0.77
    iversary
    -0.77
    urchase
    -0.72
     congratulations
    -0.72
     Congratulations
    -0.70
    DragonMagazine
    -0.70
    Cele
    -0.69
     Celebr
    -0.68
     congr
    -0.67
    POSITIVE LOGITS
     inability
    1.43
     unus
    1.34
     inadequate
    1.30
     unable
    1.29
     inefficient
    1.27
     inexper
    1.26
     lacked
    1.26
     inconsistent
    1.25
     inconsist
    1.24
     poorly
    1.23
    Activations Density 1.444%

    No Known Activations