© 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. 6688
    Prev
    Next
    INDEX
    Explanations

    words related to superlatives or rankings

    oai_token-act-pair · gpt-3.5-turbo

    key attributes or features associated with rankings and evaluations

    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
     waivers
    -0.68
     flats
    -0.67
     Jackets
    -0.66
    ¶ħ
    -0.64
     adoption
    -0.62
     employment
    -0.61
     Knights
    -0.60
    thood
    -0.60
     poisoning
    -0.60
     tubes
    -0.60
    POSITIVE LOGITS
    ented
    1.15
    iable
    1.07
    ivable
    1.07
    entious
    1.07
    icable
    1.06
    isable
    1.06
    istent
    1.05
    ested
    1.02
    izable
    1.02
    urable
    1.00
    Activations Density 0.220%

    No Known Activations