© 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. 3-RES-JB
    11. 3835
    Prev
    Next
    INDEX
    Explanations

    questions starting with "how"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "how" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agonists
    -0.66
    UME
    -0.64
    odder
    -0.62
     Mercenary
    -0.62
    ãĤ«
    -0.61
    agonist
    -0.59
    iege
    -0.59
     )]
    -0.58
    ception
    -0.58
    ceptions
    -0.57
    POSITIVE LOGITS
    soever
    0.95
    beit
    0.81
    HCR
    0.81
    ling
    0.79
    ever
    0.77
    ls
    0.75
     much
    0.74
     MUCH
    0.71
     exactly
    0.70
    much
    0.70
    Activations Density 0.069%

    No Known Activations