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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 3435
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or possibility

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovember
    -0.69
    ----------
    -0.65
    pin
    -0.63
    trap
    -0.62
     translator
    -0.61
    Typ
    -0.60
    La
    -0.60
    Released
    -0.59
    Sac
    -0.59
    idan
    -0.57
    POSITIVE LOGITS
     they
    1.06
     he
    0.89
     THEY
    0.87
    anwhile
    0.86
     she
    0.79
     it
    0.76
    they
    0.75
     we
    0.74
     there
    0.74
     none
    0.72
    Activations Density 0.305%

    No Known Activations