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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5-RES-JB
    6. 20601
    Prev
    Next
    INDEX
    Explanations

    code syntax patterns

    oai_token-act-pair · gpt-3.5-turbo

    special characters and punctuation in code or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    senal
    -0.70
    ãĥīãĥ©ãĤ´ãĥ³
    -0.69
    din
    -0.68
    atro
    -0.67
    Wars
    -0.67
    ikuman
    -0.66
    anooga
    -0.66
    iot
    -0.65
     neighb
    -0.65
    haul
    -0.64
    POSITIVE LOGITS
     };
    0.91
     }
    0.84
     //
    0.84
     });
    0.82
     /*
    0.81
    */
    0.78
    -)
    0.74
     var
    0.74
    iami
    0.73
    //
    0.71
    Activations Density 0.016%

    No Known Activations