© 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. 8-RES-JB
    11. 4215
    Prev
    Next
    INDEX
    Explanations

    adjectives describing personal qualities positively or negatively

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and phrases that describe positive and negative personality traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    doms
    -0.98
    eworks
    -0.88
    codes
    -0.87
    events
    -0.85
    lees
    -0.84
     IDs
    -0.82
    tracks
    -0.81
     visas
    -0.80
     iPads
    -0.80
    appings
    -0.80
    POSITIVE LOGITS
     liar
    1.22
     performer
    1.17
     campaigner
    1.10
     supporter
    1.09
     believer
    1.07
     participant
    1.07
     member
    1.07
     sleeper
    1.06
     lover
    1.06
     proponent
    1.05
    Activations Density 0.283%

    No Known Activations