Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 4294
    Prev
    Next
    INDEX
    Explanations

    adjectives related to rigidity or firmness

    oai_token-act-pair · gpt-3.5-turbo

    references to rigidity or stiffness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hex
    -0.76
    ulhu
    -0.72
     Paradise
    -0.69
     Occupations
    -0.67
    obyl
    -0.67
     VIDEOS
    -0.64
     Alive
    -0.64
     Ancients
    -0.63
     Partnership
    -0.63
     Scotia
    -0.62
    POSITIVE LOGITS
    eners
    1.20
    ening
    1.15
    ened
    1.07
    nesses
    1.02
    eling
    0.99
    ener
    0.96
    er
    0.96
    est
    0.96
    eness
    0.83
    ly
    0.83
    Activations Density 0.035%

    No Known Activations