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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 19792
    Prev
    Next
    INDEX
    Explanations

    references to eligibility or qualification for specific criteria, often related to legal or official requirements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate eligibility or qualification criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     goodbye
    -0.68
     parting
    -0.67
     sleeve
    -0.63
     revolving
    -0.63
     towel
    -0.61
     Lans
    -0.60
     Strauss
    -0.60
     vig
    -0.59
    vir
    -0.59
    oult
    -0.58
    POSITIVE LOGITS
     qualify
    1.10
    ifies
    1.08
    ifications
    1.05
    ifiers
    0.93
     qualified
    0.92
     qualifications
    0.90
     qualifies
    0.89
    ifying
    0.88
    ify
    0.87
    itles
    0.84
    Activations Density 0.007%

    No Known Activations