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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 760
    Prev
    Next
    INDEX
    Explanations

    phrases related to political controversies and financial ties

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods, in connection to specific phrases or claims involving political figures and events

    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
     regener
    -0.87
     happiness
    -0.86
     outdoors
    -0.80
     beginner
    -0.78
     vegetarian
    -0.78
     nodd
    -0.77
     beginners
    -0.76
     masc
    -0.74
     glim
    -0.73
     stuck
    -0.73
    POSITIVE LOGITS
    Documents
    1.51
    CIA
    1.20
    Investigators
    1.18
     Documents
    1.17
    Sources
    1.16
    According
    1.16
     Investigators
    1.14
    FBI
    1.08
     According
    1.08
    Among
    1.07
    Activations Density 0.821%

    No Known Activations