© 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. 3-RES-JB
    11. 5561
    Prev
    Next
    INDEX
    Explanations

    company names and specific terms related to telecommunication services

    oai_token-act-pair · gpt-3.5-turbo

    references to telecommunications companies and services

    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
    FUL
    -0.76
     Helpful
    -0.74
    States
    -0.73
     Disorder
    -0.72
     Definitions
    -0.72
     DPR
    -0.70
    æĸ¹
    -0.69
    ãĥĥãĥĪ
    -0.68
    ulkan
    -0.67
     Presidential
    -0.67
    POSITIVE LOGITS
     tel
    1.18
    eno
    0.95
     mosqu
    0.89
    bone
    0.87
    Tel
    0.79
    estial
    0.79
    rack
    0.78
     Aviv
    0.77
     corrid
    0.77
    esc
    0.72
    Activations Density 0.007%

    No Known Activations