© 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 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. 16671
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic journal titles

    oai_token-act-pair · gpt-3.5-turbo

    the presence of academic journal references

    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
    bucks
    -0.72
     checkpoints
    -0.70
    ickr
    -0.68
    ploy
    -0.68
     towers
    -0.67
    pload
    -0.67
     fleets
    -0.67
     compliment
    -0.66
     leaking
    -0.66
     shutting
    -0.66
    POSITIVE LOGITS
     Applied
    1.31
     Personality
    1.27
     Behavioral
    1.26
     Experimental
    1.24
     Psychology
    1.22
     Clinical
    1.19
     Compar
    1.18
     Forensic
    1.17
     Neuroscience
    1.16
     Contemporary
    1.16
    Activations Density 0.043%

    No Known Activations