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. 7-RES-JB
    6. 9229
    Prev
    Next
    INDEX
    Explanations

    phrases related to praise or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    positive assessments of various subjects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Edited
    -0.77
    DragonMagazine
    -0.71
     Disapp
    -0.68
    Occup
    -0.67
     Ago
    -0.66
    Holy
    -0.66
     Joined
    -0.66
    >>
    -0.65
     Ascension
    -0.64
     Champ
    -0.64
    POSITIVE LOGITS
     discouraged
    0.85
     exceptions
    0.84
     adamant
    0.81
     discourage
    0.80
     discour
    0.80
     examples
    0.78
     incentiv
    0.78
     plenty
    0.77
     testament
    0.76
     mitigating
    0.75
    Activations Density 0.987%

    No Known Activations