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. 21487
    Prev
    Next
    INDEX
    Explanations

    terms related to economics or financial matters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to organizations and their functions

    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
     Newsp
    -0.63
     Cf
    -0.56
    "],
    -0.56
    Newsletter
    -0.56
    ];
    -0.55
     Globe
    -0.54
    );
    -0.53
     Ov
    -0.51
     ];
    -0.51
     Md
    -0.50
    POSITIVE LOGITS
     goddamn
    0.80
     fucking
    0.77
     absolutely
    0.73
     damn
    0.72
    Pretty
    0.72
     freaking
    0.71
     basically
    0.68
     REALLY
    0.68
     insanely
    0.68
    etheless
    0.67
    Activations Density 1.771%

    No Known Activations