© 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. 6519
    Prev
    Next
    INDEX
    Explanations

    code comments starting with "How many bits" followed by code-related tokens

    oai_token-act-pair · gpt-3.5-turbo

    instances of high stress or urgency in situations

    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
    binary
    -0.77
    rad
    -0.73
    ction
    -0.72
    mbuds
    -0.70
    isons
    -0.68
    ussian
    -0.65
    abouts
    -0.63
    dit
    -0.62
    nor
    -0.61
    altern
    -0.61
    POSITIVE LOGITS
    ³³³
    0.88
    ³³³³³³³³³³³³³³³³
    0.75
    ³³³³
    0.75
     ante
    0.70
     Emanuel
    0.67
    ³³³³³³³³
    0.63
    âĵĺ
    0.61
     HA
    0.60
     Tribune
    0.58
    é¾
    0.58
    Activations Density 0.479%

    No Known Activations