© 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. 22444
    Prev
    Next
    INDEX
    Explanations

    details related to a structured process or procedure, particularly involving selection, design, or sequencing

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to selection processes or decision-making in various contexts

    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
    \.
    -0.73
    )!
    -0.66
    dylib
    -0.66
    Semitism
    -0.64
    !!
    -0.60
    alien
    -0.60
    âĹ¼
    -0.59
    ðŁĺ
    -0.59
    }}
    -0.59
     tragically
    -0.58
    POSITIVE LOGITS
    ividual
    0.92
    ministic
    0.79
     predetermined
    0.77
     upfront
    0.76
     brainstorm
    0.75
     quarterly
    0.74
     alternating
    0.74
     periodically
    0.73
     introductory
    0.73
     incremental
    0.73
    Activations Density 1.181%

    No Known Activations