Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 20699
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols

    oai_token-act-pair · gpt-3.5-turbo

    structured mathematical expressions or formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invitations
    -0.81
     cringe
    -0.80
     Skype
    -0.77
     awarding
    -0.77
     sponsorship
    -0.76
     chats
    -0.75
     elig
    -0.74
     chat
    -0.73
     solicitation
    -0.72
     sponsors
    -0.71
    POSITIVE LOGITS
    ^{
    1.57
    _{
    1.46
    \)
    1.46
    }\
    1.41
    $$
    1.39
    }}
    1.37
    (-
    1.30
    âĪĴ
    1.28
    )=
    1.28
    +(
    1.25
    Activations Density 0.063%

    No Known Activations