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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 17542
    Prev
    Next
    INDEX
    Explanations

    specific terms related to politics and current affairs

    oai_token-act-pair · gpt-3.5-turbo

    references to specific types of social or political issues and their implications

    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
     whereas
    -0.64
     Aval
    -0.63
    ]."
    -0.60
    ").
    -0.58
     UNCLASSIFIED
    -0.56
    .")
    -0.54
    "/>
    -0.53
    '."
    -0.53
     Kaplan
    -0.52
    !".
    -0.52
    POSITIVE LOGITS
     alike
    1.15
     thereof
    0.89
    asions
    0.73
    cellaneous
    0.71
    depending
    0.69
     respectively
    0.67
     thereto
    0.67
    ggles
    0.65
     versa
    0.64
    rosso
    0.61
    Activations Density 1.040%

    No Known Activations