© 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. 2-RES-JB
    11. 15732
    Prev
    Next
    INDEX
    Explanations

    expressions indicating certainty or uncertainty, such as "no doubt", "doubt", or "wonder"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express certainty or skepticism

    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
    ahime
    -0.83
    don
    -0.74
    visor
    -0.65
    ili
    -0.61
    alysis
    -0.61
    ulner
    -0.60
    weeney
    -0.60
    ork
    -0.60
    itton
    -0.60
    zbollah
    -0.60
    POSITIVE LOGITS
     whatsoever
    1.71
     nor
    1.33
     anymore
    1.25
     except
    0.91
     anywhere
    0.89
    yet
    0.88
     anything
    0.82
     anybody
    0.81
    except
    0.79
     anyone
    0.78
    Activations Density 0.612%

    No Known Activations