© 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. 7-RES-JB
    11. 14739
    Prev
    Next
    INDEX
    Explanations

    words related to feelings of uncertainty or conflict

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ambiguity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ppo
    -0.80
    creen
    -0.76
    fork
    -0.68
    MET
    -0.68
    tten
    -0.68
    leaf
    -0.67
    ãĥīãĥ©ãĤ´ãĥ³
    -0.66
     Coffin
    -0.65
    vous
    -0.65
     Soda
    -0.64
    POSITIVE LOGITS
    iance
    1.26
    assad
    1.18
    ivalent
    1.18
    ushed
    1.06
    ience
    1.05
    ushes
    1.04
    acity
    1.02
    assador
    1.00
    iguous
    0.99
    acious
    0.97
    Activations Density 0.023%

    No Known Activations