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. 6-RES-JB
    6. 21672
    Prev
    Next
    INDEX
    Explanations

    action verbs indicating physical or dynamic movement

    oai_token-act-pair · gpt-3.5-turbo

    active verbs related to characters taking significant actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arta
    -0.64
    cedented
    -0.62
    been
    -0.60
    esa
    -0.58
    league
    -0.57
    enta
    -0.57
    arel
    -0.57
    yet
    -0.55
    veland
    -0.54
    venge
    -0.54
    POSITIVE LOGITS
    nesday
    0.73
     unsuccessfully
    0.63
     tremend
    0.62
    ĸļ
    0.59
    JV
    0.57
    Ô
    0.53
    ãĤ¤ãĥĪ
    0.52
    perty
    0.51
     pione
    0.51
     voic
    0.50
    Activations Density 0.703%

    No Known Activations