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. 0-RES-JB
    6. 7365
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, particularly those ending in 'Fer'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals with the surname "Fer."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eka
    -0.91
    HUD
    -0.85
     widget
    -0.82
     00000000
    -0.74
    tnc
    -0.74
     widgets
    -0.72
     amnesty
    -0.71
    sn
    -0.71
    tn
    -0.69
     ACA
    -0.67
    POSITIVE LOGITS
     Fer
    3.86
    Fer
    2.90
     fer
    1.93
     Ferr
    1.59
    fer
    1.31
     Tur
    1.26
     Fib
    1.24
     Fou
    1.20
     Fro
    1.19
     ferment
    1.18
    Activations Density 0.015%

    No Known Activations