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. 8-RES-JB
    6. 17947
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions, achievements, and characteristics

    oai_token-act-pair · gpt-3.5-turbo

    action-oriented words related to providing, building, and understanding in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     .)
    -0.88
    .]
    -0.81
     nutshell
    -0.74
    emen
    -0.67
    âĢķ
    -0.67
    .)
    -0.67
     âĢķ
    -0.66
     |
    -0.66
    WAR
    -0.61
    SPONSORED
    -0.60
    POSITIVE LOGITS
    agher
    0.62
    leanor
    0.60
    lete
    0.57
    lda
    0.57
     Falk
    0.56
    utils
    0.53
    $,
    0.53
    agne
    0.53
     Shogun
    0.53
     etc
    0.53
    Activations Density 0.461%

    No Known Activations