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

    Neuronpedia

    APICircuit 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. 14651
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, specifically ending with 'ios'

    oai_token-act-pair · gpt-3.5-turbo

    references to the iOS operating system

    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
     speaker
    -0.72
     Springfield
    -0.65
     Guantanamo
    -0.61
     sharply
    -0.61
     parliamentary
    -0.60
     bom
    -0.59
     sequest
    -0.59
     Parliamentary
    -0.59
     taxpayer
    -0.59
     Parliament
    -0.58
    POSITIVE LOGITS
    ios
    4.78
    io
    2.14
    ias
    1.67
    IO
    1.64
    iod
    1.63
    iop
    1.61
    iot
    1.59
    ius
    1.47
    iol
    1.37
    iov
    1.31
    Activations Density 0.008%

    No Known Activations