© 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. 20414
    Prev
    Next
    INDEX
    Explanations

    occurrences where the prefix "ex-" is used

    oai_token-act-pair · gpt-3.5-turbo

    the prefix "ex" indicating the state of having been or the past relationship of people or things

    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
    ãĤ¤ãĥĪ
    -0.67
    arity
    -0.66
     GOODMAN
    -0.63
     Sawyer
    -0.59
     Drawn
    -0.57
     revolving
    -0.57
    OUP
    -0.56
     realism
    -0.56
     poisoning
    -0.55
     blindness
    -0.54
    POSITIVE LOGITS
    clamation
    1.49
    uber
    1.33
    orbit
    1.31
    ogenous
    1.19
    oplan
    1.15
    portation
    1.14
    tern
    1.14
    commun
    1.12
    clud
    1.10
    communication
    1.10
    Activations Density 0.012%

    No Known Activations