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. 6-RES-JB
    6. 24262
    Prev
    Next
    INDEX
    Explanations

    specific names/entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Owens" and its variations, as well as related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĸ¬
    -0.83
    iard
    -0.75
    ministic
    -0.68
    places
    -0.66
    acters
    -0.66
    ++++++++++++++++
    -0.66
    plane
    -0.65
    ãĤ¼ãĤ¦ãĤ¹
    -0.65
    pai
    -0.65
    flies
    -0.63
    POSITIVE LOGITS
    yssey
    1.05
    landish
    0.81
    atmeal
    0.80
    toc
    0.79
    scill
    0.77
    ceans
    0.76
    boro
    0.76
    ikawa
    0.75
    cean
    0.74
    mega
    0.72
    Activations Density 0.071%

    No Known Activations