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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3785
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rein" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rein" and its variations in context, indicating a focus on restoration or reinstatement themes

    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
    UGH
    -0.75
     Borough
    -0.74
    DragonMagazine
    -0.73
     Emin
    -0.70
     Correspond
    -0.67
     Occupations
    -0.67
    ertodd
    -0.67
     handwriting
    -0.64
     Organisation
    -0.63
    INGS
    -0.62
    POSITIVE LOGITS
    vention
    1.37
    statement
    1.32
    stall
    1.26
    itial
    1.21
    itialized
    1.11
    cess
    1.03
    visor
    1.01
    forcer
    0.98
    vision
    0.93
    fect
    0.93
    Activations Density 0.014%

    No Known Activations