© 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. 10-RES-JB
    11. 7311
    Prev
    Next
    INDEX
    Explanations

    words related to achieving approval or vindication through evidence or demonstration

    oai_token-act-pair · gpt-3.5-turbo

    references to business strategies and financial obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anon
    -0.79
    Joined
    -0.65
    gay
    -0.63
     segregation
    -0.63
     Died
    -0.63
    OTOS
    -0.62
     homosexuality
    -0.61
     edits
    -0.60
     lyrics
    -0.60
     Installation
    -0.60
    POSITIVE LOGITS
     gamb
    0.93
     strateg
    0.93
     shrew
    0.92
     hoping
    0.87
     reap
    0.87
     bluff
    0.87
     sorely
    0.84
     understandably
    0.83
     capitalize
    0.83
     relying
    0.82
    Activations Density 0.451%

    No Known Activations