© 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. 14072
    Prev
    Next
    INDEX
    Explanations

    phrases related to analyzing or commenting on data, statistics, or conclusions

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to social constructs and their critiques

    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
    boarding
    -0.76
    ioch
    -0.72
    quished
    -0.68
     Talks
    -0.67
     Immediately
    -0.66
     thanked
    -0.65
    llular
    -0.65
     Pwr
    -0.64
     greets
    -0.64
    thouse
    -0.62
    POSITIVE LOGITS
     misleading
    1.48
     flawed
    1.37
     inaccurate
    1.34
     simplistic
    1.32
     overs
    1.28
     faulty
    1.27
     miscon
    1.25
     misguided
    1.24
     erroneous
    1.23
     misplaced
    1.21
    Activations Density 0.280%

    No Known Activations