© 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. 13785
    Prev
    Next
    INDEX
    Explanations

    phrases where the speaker expresses their opinion about a particular situation or topic

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinion or belief

    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
     unavailable
    -0.83
    éĹĺ
    -0.73
    ãĥīãĥ©
    -0.68
     Not
    -0.68
    none
    -0.66
    ãĤ´ãĥ³
    -0.65
     Unknown
    -0.64
    è¦ļéĨĴ
    -0.64
    éŃĶ
    -0.59
    ãĥĭ
    -0.57
    POSITIVE LOGITS
     underrated
    1.04
     deserved
    0.96
     deserves
    0.94
     underest
    0.93
     underestimate
    0.89
     underestimated
    0.89
     overest
    0.87
     deserve
    0.86
     fair
    0.86
     faire
    0.83
    Activations Density 0.268%

    No Known Activations