© 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. 6-RES-JB
    11. 13791
    Prev
    Next
    INDEX
    Explanations

    words related to updates or the most current information

    oai_token-act-pair · gpt-3.5-turbo

    hyphenated phrases or words that indicate a list or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lumpur
    -0.74
     Phi
    -0.73
    uania
    -0.72
     Wiz
    -0.70
     Kern
    -0.69
    ulhu
    -0.67
     Cec
    -0.66
     Consent
    -0.65
    ãģ®éŃĶ
    -0.65
     EntityItem
    -0.64
    POSITIVE LOGITS
    graded
    1.24
    sized
    1.18
    based
    1.03
    to
    1.02
    themed
    1.00
    grading
    0.96
    tem
    0.95
    grade
    0.93
    ended
    0.92
    bodied
    0.92
    Activations Density 0.098%

    No Known Activations