© 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. 11-RES-JB
    11. 1400
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the speaker's opinion on a suggested course of action

    oai_token-act-pair · gpt-3.5-turbo

    expressions of the opinion that something is a good idea or positive

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lers
    -0.78
    eds
    -0.76
    RAW
    -0.76
    ngth
    -0.74
    hyde
    -0.74
    pez
    -0.70
    UF
    -0.70
    cs
    -0.68
     Pages
    -0.67
    vt
    -0.66
    POSITIVE LOGITS
     thing
    1.38
     idea
    1.36
     indicator
    1.23
     indication
    1.12
     predictor
    1.12
     fit
    1.09
     bet
    1.07
     place
    1.06
     excuse
    1.04
     sign
    1.04
    Activations Density 0.077%

    No Known Activations