© 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 EvalsExportsinterp-engineNEWAPI 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. 14381
    Prev
    Next
    INDEX
    Explanations

    conceptual words related to reasoning or causation

    oai_token-act-pair · gpt-3.5-turbo

    concepts and terms related to reasoning and logic

    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
    ynchron
    -0.66
    ystem
    -0.63
     active
    -0.58
     concess
    -0.58
     ecosystem
    -0.55
     flexible
    -0.55
    insula
    -0.55
     stable
    -0.54
     GPL
    -0.54
     landscape
    -0.53
    POSITIVE LOGITS
    lessness
    0.98
    istically
    0.89
    ously
    0.84
     alone
    0.82
    ality
    0.82
    lessly
    0.82
    istic
    0.80
    lication
    0.79
    fulness
    0.76
     sake
    0.74
    Activations Density 0.400%

    No Known Activations