© 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. 10-RES-JB
    11. 2273
    Prev
    Next
    INDEX
    Explanations

    words related to critiquing or commenting on actions or decisions made by individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "for" indicating support or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ieth
    -0.74
    OTAL
    -0.70
    oya
    -0.70
    DragonMagazine
    -0.69
    icka
    -0.67
    sonian
    -0.66
    iple
    -0.65
    soever
    -0.63
    illin
    -0.62
    ixon
    -0.62
    POSITIVE LOGITS
     failing
    1.45
     refusing
    1.28
     abandoning
    1.21
     ignoring
    1.18
     underest
    1.17
     allegedly
    1.16
     lacking
    1.14
     mishand
    1.13
     wasting
    1.12
     inaction
    1.12
    Activations Density 0.114%

    No Known Activations