© 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. 2-RES-JB
    11. 21051
    Prev
    Next
    INDEX
    Explanations

    adjectives related to physical appearance and condition

    oai_token-act-pair · gpt-3.5-turbo

    adjectives describing qualities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptions
    -0.75
    ENTS
    -0.72
     sidx
    -0.72
    PRES
    -0.69
    ULTS
    -0.69
     Peninsula
    -0.69
     Partnership
    -0.67
    hler
    -0.64
    utory
    -0.63
    izoph
    -0.63
    POSITIVE LOGITS
    ness
    1.40
    ly
    1.08
    nesses
    1.05
    eness
    0.99
    ening
    0.97
    est
    0.95
    idious
    0.86
    ened
    0.84
    iness
    0.78
    ocity
    0.78
    Activations Density 0.011%

    No Known Activations