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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 6956
    Prev
    Next
    INDEX
    Explanations

    adjectives related to interpretation or personal judgment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to subjectivity and the subjective nature of experiences or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    flies
    -0.89
    letters
    -0.86
     Tycoon
    -0.80
    bowl
    -0.75
    fly
    -0.74
    letter
    -0.68
    birds
    -0.67
    nz
    -0.67
    RNA
    -0.67
     Eggs
    -0.67
    POSITIVE LOGITS
     judgement
    1.02
     subjective
    0.98
     pronoun
    0.90
     judgment
    0.89
     minded
    0.87
     wellbeing
    0.85
     livest
    0.85
     analy
    0.84
     opinions
    0.83
     pronouns
    0.80
    Activations Density 0.021%

    No Known Activations