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. 10-RES-JB
    6. 19418
    Prev
    Next
    INDEX
    Explanations

    words related to issues in scalability and crimes

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with crime and scalability issues in various contexts

    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
     Sacrament
    -0.70
    ANGE
    -0.68
     Congo
    -0.61
     Flight
    -0.60
     Franç
    -0.60
     Torah
    -0.59
     Oriental
    -0.59
     stronghold
    -0.58
    #$
    -0.58
    OWN
    -0.57
    POSITIVE LOGITS
    etime
    1.45
    ulative
    1.41
    eworks
    1.33
    elines
    1.27
    ming
    1.24
    eless
    1.17
    emaker
    1.13
    ework
    1.11
    emen
    1.11
    eline
    1.06
    Activations Density 0.052%

    No Known Activations