© 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. 10-RES-JB
    11. 20657
    Prev
    Next
    INDEX
    Explanations

    negative evaluations or criticisms

    oai_token-act-pair · gpt-3.5-turbo

    negative assessments or criticisms of arguments and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gins
    -0.71
    interrupted
    -0.69
    ahs
    -0.69
     downed
    -0.66
    ien
    -0.65
    rollers
    -0.65
     dreaded
    -0.63
    ominated
    -0.62
    Phones
    -0.62
    mins
    -0.61
    POSITIVE LOGITS
     insofar
    0.96
     because
    0.87
     extrap
    0.83
     unless
    0.81
    ctive
    0.77
     considering
    0.77
     enough
    0.76
     nonetheless
    0.76
     nonsense
    0.74
    headed
    0.74
    Activations Density 0.151%

    No Known Activations