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. 22102
    Prev
    Next
    INDEX
    Explanations

    adjectives describing subjective experiences

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that express emotional reactions or assessments

    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
    classes
    -0.84
    apons
    -0.83
    tracks
    -0.82
    ravings
    -0.80
    artifacts
    -0.80
    units
    -0.80
    iencies
    -0.79
    ummies
    -0.79
    lees
    -0.78
    ptives
    -0.77
    POSITIVE LOGITS
     thing
    1.40
     proposition
    1.22
     occurrence
    1.20
     reminder
    1.20
     topic
    1.19
     situation
    1.17
     statement
    1.14
     tactic
    1.13
     endeavor
    1.12
     phenomenon
    1.11
    Activations Density 0.198%

    No Known Activations