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. 1-RES-JB
    6. 9688
    Prev
    Next
    INDEX
    Explanations

    technical terms and proper nouns related to technology and events

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to organizations, events, or notable locations

    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
    iosyn
    -0.63
    rez
    -0.53
    requires
    -0.53
    NetMessage
    -0.51
     WCS
    -0.50
    hem
    -0.49
    iple
    -0.49
     Planes
    -0.47
    MW
    -0.46
    URI
    -0.45
    POSITIVE LOGITS
    ioxide
    0.71
    estern
    0.65
    eers
    0.62
     imitation
    0.59
    culosis
    0.58
    kees
    0.57
    isconsin
    0.57
    uyomi
    0.56
    ertodd
    0.55
    ictionary
    0.54
    Activations Density 1.823%

    No Known Activations