© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 10234
    Prev
    Next
    INDEX
    Explanations

    phrases or adjectives related to specific conditions or specifications

    oai_token-act-pair · gpt-3.5-turbo

    the concept of 'certain' or specific conditions and circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thence
    -0.79
    NAS
    -0.75
    ĺħ
    -0.65
    dl
    -0.63
    Adds
    -0.62
    Fal
    -0.62
    archive
    -0.60
    âĸº
    -0.60
     EVER
    -0.60
    usk
    -0.60
    POSITIVE LOGITS
    ties
    1.62
     kinds
    1.42
     types
    1.35
     aspects
    1.17
     segments
    1.06
     sections
    1.05
     embodiments
    1.03
     wavelengths
    1.03
    iating
    1.02
     parts
    1.00
    Activations Density 0.048%

    No Known Activations