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. 9-RES-JB
    6. 12680
    Prev
    Next
    INDEX
    Explanations

    words related to negative financial situations or conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to negative outcomes and failures in various contexts

    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
    verning
    -0.77
    negie
    -0.73
    igham
    -0.73
    sonian
    -0.69
    ortium
    -0.67
    ceivable
    -0.67
    çīĪ
    -0.66
     fabulous
    -0.64
     exquisite
    -0.64
    atorium
    -0.63
    POSITIVE LOGITS
     syndrome
    0.95
     Syndrome
    0.92
     Practices
    0.87
    behavior
    0.78
     imaginable
    0.77
     perpetrated
    0.75
     habits
    0.73
     practices
    0.69
    glers
    0.69
     caused
    0.68
    Activations Density 0.479%

    No Known Activations