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. 1-RES-JB
    6. 17119
    Prev
    Next
    INDEX
    Explanations

    words related to keratin, a protein found in human nails and other materials

    oai_token-act-pair · gpt-3.5-turbo

    linguistic components or elements related to specific suffixes or prefixes, particularly in terms related to 'atin', 'oling', and 'ocon'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lying
    -0.80
    LEASE
    -0.77
     GEAR
    -0.75
    Availability
    -0.71
     ancest
    -0.70
     mistress
    -0.70
    Created
    -0.70
    ŀ
    -0.68
    ŃĶ
    -0.67
    =-=-=-=-
    -0.65
    POSITIVE LOGITS
    atin
    1.53
    obin
    1.05
    atown
    1.03
    ocytes
    1.02
    enos
    0.98
    osaurs
    0.98
    ocular
    0.96
    htaking
    0.93
    ny
    0.92
    okia
    0.91
    Activations Density 0.009%

    No Known Activations