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. 6-RES-JB
    6. 20950
    Prev
    Next
    INDEX
    Explanations

    commands or strong statements

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with action-oriented social or organizational initiatives

    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
    mith
    -0.76
    emale
    -0.67
    terday
    -0.65
    cffffcc
    -0.63
     disg
    -0.62
    tnc
    -0.60
    dk
    -0.59
    hell
    -0.59
     stride
    -0.57
    ilver
    -0.56
    POSITIVE LOGITS
     Yourself
    1.26
     yourselves
    1.16
     yourself
    1.11
    ings
    1.07
    ables
    1.02
    ments
    0.98
    able
    0.93
    acion
    0.90
    tainment
    0.89
     Your
    0.89
    Activations Density 0.281%

    No Known Activations