Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 9268
    Prev
    Next
    INDEX
    Explanations

    positive adjectives or superlatives

    oai_token-act-pair · gpt-3.5-turbo

    superlative adjectives expressing positive or negative evaluations

    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
    é¾į
    -0.82
    çīĪ
    -0.81
    ymes
    -0.81
    dinand
    -0.80
    ãĥīãĥ©
    -0.80
    appings
    -0.79
    èĪ
    -0.79
    ittees
    -0.75
    ilings
    -0.74
    İĭ
    -0.73
    POSITIVE LOGITS
     thing
    1.43
     imaginable
    1.10
     conceivable
    0.93
     EVER
    0.91
     ever
    0.89
     aspect
    0.88
     way
    0.85
     Thing
    0.84
    thing
    0.84
     possible
    0.82
    Activations Density 0.159%

    No Known Activations