© 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. 9-RES-JB
    11. 15416
    Prev
    Next
    INDEX
    Explanations

    superlatives and positive adjectives related to various objects and experiences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "The" likely indicating a focus on prominent features or highlights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thood
    -0.83
     voluntarily
    -0.79
     thereby
    -0.79
    Ó
    -0.77
    ailable
    -0.76
    ashington
    -0.74
    rolet
    -0.73
    stretched
    -0.73
    leground
    -0.72
     according
    -0.72
    POSITIVE LOGITS
     biggest
    1.23
    oret
    1.16
     downside
    1.16
     hardest
    1.14
     coolest
    1.12
    resa
    1.05
     easiest
    1.05
     thing
    1.04
     slightest
    1.03
     irony
    1.00
    Activations Density 0.405%

    No Known Activations