© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 10922
    Prev
    Next
    INDEX
    Explanations

    verbs related to moving upwards or improving in rank or position

    oai_token-act-pair · gpt-3.5-turbo

    references to movement or ascent

    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
    ATA
    -0.71
    Maker
    -0.66
     Emanuel
    -0.65
    [/
    -0.64
    ¯¯¯¯¯¯¯¯
    -0.60
    Synopsis
    -0.60
    ________________________
    -0.60
    Closure
    -0.59
    士
    -0.59
    TY
    -0.59
    POSITIVE LOGITS
    stairs
    1.18
    rights
    1.00
    river
    1.00
    stage
    0.97
     stairs
    0.95
    graded
    0.94
    grading
    0.91
    grades
    0.90
    dates
    0.83
    dating
    0.83
    Activations Density 0.062%

    No Known Activations