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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 3029
    Prev
    Next
    INDEX
    Explanations

    references to adaptations from one form of media to another

    oai_token-act-pair · gpt-3.5-turbo

    terms related to adaptations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mouth
    -0.76
    sonian
    -0.72
    ²¾
    -0.72
    adows
    -0.70
     Vall
    -0.70
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.69
    âĸ¬
    -0.69
    phalt
    -0.69
    etsk
    -0.67
    ¯¯¯¯¯¯¯¯
    -0.65
    POSITIVE LOGITS
     adaptation
    1.31
     adaptations
    1.13
    adapt
    0.93
     adapted
    0.90
     screenplay
    0.89
     Adapt
    0.88
     adapting
    0.82
     adapt
    0.78
    xual
    0.78
    folios
    0.73
    Activations Density 0.010%

    No Known Activations