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

    Neuronpedia

    APICircuit 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. 4-RES-JB
    6. 3555
    Prev
    Next
    INDEX
    Explanations

    terms related to coding and software development

    oai_token-act-pair · gpt-3.5-turbo

    elements related to success or failure in ventures

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

    No Comments

    Negative Logits
     thereof
    -0.53
     thereto
    -0.52
     guiActiveUnfocused
    -0.49
    .</
    -0.48
    $.
    -0.47
     respectively
    -0.45
    Reilly
    -0.45
    .).
    -0.45
     outwe
    -0.45
    .''
    -0.45
    POSITIVE LOGITS
     meanwhile
    0.51
     Edit
    0.45
    ibliography
    0.44
    ':
    0.43
    prisingly
    0.42
    endum
    0.42
     Profile
    0.41
     Lavrov
    0.41
     FANTASY
    0.40
     âĵĺ
    0.40
    Activations Density 5.080%

    No Known Activations