© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11118
    Prev
    Next
    INDEX
    Explanations

    possessive nouns ending in 's

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 's'

    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
    bp
    -0.67
    Compare
    -0.64
    ISON
    -0.64
    wright
    -0.63
    roup
    -0.61
    Reference
    -0.60
    ient
    -0.60
    roups
    -0.60
    endez
    -0.60
     Lauder
    -0.60
    POSITIVE LOGITS
     demise
    1.09
    ELF
    1.07
     shortcomings
    1.01
     existence
    0.99
     reputation
    0.95
     own
    0.93
     ability
    0.93
     fate
    0.89
     failings
    0.89
     popularity
    0.89
    Activations Density 0.204%

    No Known Activations