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. 7-RES-JB
    6. 23768
    Prev
    Next
    INDEX
    Explanations

    words related to external intervention or involvement in a situation

    oai_token-act-pair · gpt-3.5-turbo

    references to interference, particularly in political or electoral contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndra
    -0.75
    chal
    -0.71
    carbon
    -0.70
     Fight
    -0.70
    itan
    -0.67
    uber
    -0.66
    sword
    -0.66
    chat
    -0.65
    itudes
    -0.63
    Template
    -0.63
    POSITIVE LOGITS
     tampering
    0.86
     interfere
    0.84
     interference
    0.79
     interfering
    0.78
     meddling
    0.77
    ially
    0.76
     interfered
    0.74
     intr
    0.72
     peripher
    0.71
     medd
    0.70
    Activations Density 0.028%

    No Known Activations