© 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. 7-RES-JB
    11. 13354
    Prev
    Next
    INDEX
    Explanations

    instances where something is discovered or observed

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the discovery of something unexpected or significant

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     derog
    -0.83
    vote
    -0.72
    jong
    -0.70
    ongo
    -0.69
    escal
    -0.69
    xus
    -0.67
    commit
    -0.67
     derivative
    -0.67
    otine
    -0.67
    imo
    -0.66
    POSITIVE LOGITS
     waking
    0.76
     lifeless
    0.72
    LESS
    0.72
     greeted
    0.70
     beautiful
    0.69
    tons
    0.67
     emptiness
    0.67
     behold
    0.66
     reapp
    0.66
     snowy
    0.66
    Activations Density 0.200%

    No Known Activations