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. 4-RES-JB
    6. 18809
    Prev
    Next
    INDEX
    Explanations

    words related to negative consequences or actions

    oai_token-act-pair · gpt-3.5-turbo

    themes related to health, financial issues, and socio-political challenges

    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
     depress
    -0.50
    pop
    -0.48
    cknow
    -0.47
    going
    -0.46
     studied
    -0.46
    ifted
    -0.46
     hail
    -0.44
    cknowled
    -0.44
     beh
    -0.44
    enne
    -0.43
    POSITIVE LOGITS
    20439
    0.55
     ashore
    0.54
    ylum
    0.54
    ocobo
    0.54
     Afgh
    0.53
     whilst
    0.53
    Reloaded
    0.51
     Salvador
    0.51
    Eva
    0.50
    ãĢĤ
    0.50
    Activations Density 1.191%

    No Known Activations