© 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. 2-RES-JB
    6. 12716
    Prev
    Next
    INDEX
    Explanations

    words related to contradiction or opposing views

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Cont" and its variations, indicating a focus on contrasting statements or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStream
    -1.12
    ħĭ
    -0.85
    STER
    -0.81
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.80
    senal
    -0.76
    Downloadha
    -0.75
    OPLE
    -0.74
    Reviewer
    -0.72
    terday
    -0.72
    steen
    -0.72
    POSITIVE LOGITS
    ributed
    1.21
    ribution
    1.20
    ainment
    1.16
    ribut
    1.09
    rast
    1.07
    ribute
    1.05
    roversial
    1.02
    ainers
    0.97
    rollers
    0.94
    rad
    0.93
    Activations Density 0.010%

    No Known Activations