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. 6-RES-JB
    6. 12410
    Prev
    Next
    INDEX
    Explanations

    political entities and terms related to government and military

    oai_token-act-pair · gpt-3.5-turbo

    references to political parties and governmental entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ttp
    -0.74
    SPONSORED
    -0.71
    é¾įå¥ij士
    -0.69
    âĵĺ
    -0.64
    ãģĻ
    -0.64
    externalActionCode
    -0.64
    appropriate
    -0.63
     guiActiveUnfocused
    -0.61
    Charges
    -0.60
    ãģĨ
    -0.60
    POSITIVE LOGITS
     certainly
    0.75
     retains
    0.73
     consists
    0.72
     cannot
    0.71
     reverted
    0.69
     fared
    0.69
     thri
    0.68
     lacks
    0.68
     embodies
    0.67
     unquestion
    0.67
    Activations Density 0.903%

    No Known Activations