© 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. 7-RES-JB
    11. 2205
    Prev
    Next
    INDEX
    Explanations

    phrases related to intention, purpose or strategy

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating methods or ways of achieving objectives or making a point

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tis
    -1.13
    */
    -0.80
     Indigo
    -0.79
    semble
    -0.74
    stars
    -0.74
    omes
    -0.70
     Elements
    -0.69
     Tos
    -0.68
     TJ
    -0.67
    modules
    -0.67
    POSITIVE LOGITS
     pretext
    1.25
     excuse
    1.12
     blackmail
    1.11
     ploy
    1.06
     justify
    0.98
     circumvent
    0.98
     leverage
    0.96
     justifying
    0.95
     distract
    0.92
     justification
    0.91
    Activations Density 0.563%

    No Known Activations