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. 10-RES-JB
    6. 20940
    Prev
    Next
    INDEX
    Explanations

    words related to verification, accuracy, and validation

    oai_token-act-pair · gpt-3.5-turbo

    words related to verification or authenticity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hybrids
    -0.65
    ered
    -0.63
     Fever
    -0.63
     undergoing
    -0.61
     Towns
    -0.60
     Warriors
    -0.60
     listening
    -0.60
     Rh
    -0.59
     experimenting
    -0.59
     resid
    -0.59
    POSITIVE LOGITS
    ifiable
    1.44
    itable
    1.36
    itably
    1.22
    bat
    1.18
    acity
    1.10
    anda
    1.08
    gence
    1.08
    onica
    1.05
    ifies
    1.02
    izon
    1.01
    Activations Density 0.021%

    No Known Activations