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. 21236
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "By" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "By," indicating instructions, actions, or methods

    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
    ickets
    -0.67
     pains
    -0.63
    SPONSORED
    -0.61
     Cabin
    -0.61
     digs
    -0.61
    icken
    -0.60
    MpServer
    -0.59
    itives
    -0.59
    umble
    -0.59
    earable
    -0.57
    POSITIVE LOGITS
     contrast
    1.32
     virtue
    1.14
     implication
    1.04
    catch
    1.01
    akuya
    0.97
    product
    0.89
     sheer
    0.89
     analogy
    0.88
    stand
    0.88
     extension
    0.88
    Activations Density 0.041%

    No Known Activations