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. 0-RES-JB
    6. 11074
    Prev
    Next
    INDEX
    Explanations

    phrases related to increasing or intensifying activity or production

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ramp," indicating discussions around increasing or enhancing efforts or infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onyms
    -0.71
    acea
    -0.69
    ensus
    -0.69
    ody
    -0.68
    ties
    -0.66
    ession
    -0.66
    dat
    -0.65
     Editors
    -0.64
    >>
    -0.64
    ividually
    -0.64
    POSITIVE LOGITS
     ramp
    3.86
     ramps
    2.86
     Ramp
    2.24
     escal
    1.16
     spike
    1.10
     railing
    1.06
     rampage
    1.04
     thrott
    1.03
     spikes
    1.03
     escalated
    1.03
    Activations Density 0.013%

    No Known Activations