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. 22811
    Prev
    Next
    INDEX
    Explanations

    chemical names and related terms

    oai_token-act-pair · gpt-3.5-turbo

    chemical compounds and their environmental impacts

    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
     Eag
    -0.76
    hess
    -0.73
     Jury
    -0.71
    MENTS
    -0.69
    Students
    -0.67
    rick
    -0.65
    iHUD
    -0.64
     Griffin
    -0.64
    Student
    -0.64
     Hutch
    -0.64
    POSITIVE LOGITS
     oxid
    1.00
     phosphate
    0.96
     contamin
    0.92
     soluble
    0.92
     chemically
    0.92
     phosphorus
    0.91
     combustion
    0.91
     acidic
    0.85
     electroly
    0.85
     ammon
    0.84
    Activations Density 0.910%

    No Known Activations