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. 3-RES-JB
    6. 18801
    Prev
    Next
    INDEX
    Explanations

    references to legal or law enforcement entities and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to "woman" and "roman" in various contexts, suggesting a focus on gender-related themes or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    casting
    -0.77
    Reviewer
    -0.77
     Emin
    -0.72
    llular
    -0.68
    UV
    -0.67
    IRO
    -0.67
    REE
    -0.67
    rared
    -0.66
    maxwell
    -0.66
    IRD
    -0.65
    POSITIVE LOGITS
    ufact
    1.30
    agement
    1.09
    oman
    1.08
    ry
    0.84
    ipal
    0.82
    ation
    0.81
    agements
    0.81
    thal
    0.80
    WithNo
    0.79
    ovember
    0.78
    Activations Density 0.011%

    No Known Activations