© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 2169
    Prev
    Next
    INDEX
    Explanations

    adjectives related to the evaluation or perception of something, particularly emphasizing subjectivity

    oai_token-act-pair · gpt-3.5-turbo

    the concept of subjectivity in perceptions and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ews
    -0.77
    unic
    -0.76
     Tackle
    -0.75
    Lock
    -0.71
    Guard
    -0.70
    zz
    -0.69
     Sand
    -0.67
    guard
    -0.66
    dragon
    -0.66
    icer
    -0.64
    POSITIVE LOGITS
     subjective
    3.61
     objectively
    1.41
     qualitative
    1.41
     anecdotal
    1.33
     perceptual
    1.30
     objective
    1.20
     situational
    1.16
     subconscious
    1.15
     methodological
    1.12
    subject
    1.09
    Activations Density 0.026%

    No Known Activations