© 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. 4563
    Prev
    Next
    INDEX
    Explanations

    terms related to technical or specialized jargon and terms

    oai_token-act-pair · gpt-3.5-turbo

    symbols or representations associated with emotional or narrative themes

    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
     sacrific
    -0.66
     STATES
    -0.65
     mathemat
    -0.64
     seiz
    -0.63
     Seym
    -0.62
     delegation
    -0.62
     proble
    -0.61
     artific
    -0.60
    achus
    -0.60
     federation
    -0.59
    POSITIVE LOGITS
    ï¸ı
    1.22
    esc
    0.85
    £
    0.82
    etc
    0.73
    §
    0.73
    tracks
    0.71
    ual
    0.70
    eric
    0.70
    ãĤĭ
    0.70
    ution
    0.70
    Activations Density 0.185%

    No Known Activations