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. 12641
    Prev
    Next
    INDEX
    Explanations

    mentions of severance packages or payments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to severance or termination payments

    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
    ioch
    -0.87
    ickr
    -0.69
    iggs
    -0.69
    iard
    -0.67
     unaccompanied
    -0.62
    eus
    -0.61
     moderates
    -0.59
    ussy
    -0.59
     Notting
    -0.59
    Appearances
    -0.58
    POSITIVE LOGITS
     sever
    1.24
     severed
    1.08
     limb
    0.99
    lass
    0.88
     limbs
    0.86
    butt
    0.85
    tle
    0.85
    cut
    0.81
    ricular
    0.80
    lasses
    0.79
    Activations Density 0.018%

    No Known Activations