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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20344
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and organizations

    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
     VID
    -0.70
     entitle
    -0.68
     Kers
    -0.63
     tyr
    -0.62
     skelet
    -0.62
     entitlement
    -0.60
     warr
    -0.59
     welf
    -0.58
     PAX
    -0.58
     backlog
    -0.58
    POSITIVE LOGITS
    Saharan
    0.82
    tein
    0.78
    akra
    0.73
    acher
    0.73
    roid
    0.72
    ®
    0.71
    ®,
    0.70
    hedral
    0.69
     Jinping
    0.68
    igger
    0.66
    Activations Density 0.314%

    No Known Activations