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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5195
    Prev
    Next
    INDEX
    Explanations

    text related to academic courses, coaching, mentoring, data plans, property damage, voting, self-guided walking tours, and presentations

    oai_token-act-pair · gpt-3.5-turbo

    references to academic or educational programs and opportunities

    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
    ĸļ
    -0.87
    xual
    -0.71
     Leilan
    -0.71
    illance
    -0.65
     Gaal
    -0.65
    ascus
    -0.64
    iga
    -0.64
     Miko
    -0.63
     mod
    -0.62
    ussia
    -0.62
    POSITIVE LOGITS
    IPS
    0.88
    ————————
    0.85
    Individual
    0.80
    Synopsis
    0.79
    IPP
    0.78
    Optional
    0.77
    each
    0.76
    CRE
    0.76
    Enter
    0.76
    Avoid
    0.76
    Activations Density 0.330%

    No Known Activations