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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24289
    Prev
    Next
    INDEX
    Explanations

    sequences of characters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sequencing and sequential processes

    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
     Wel
    -0.82
     Owner
    -0.75
     Proud
    -0.74
     CoC
    -0.69
    cks
    -0.68
    lord
    -0.68
    HB
    -0.67
    oney
    -0.67
     Defender
    -0.66
     Blessing
    -0.65
    POSITIVE LOGITS
     sequ
    4.59
    sequ
    2.79
     Sequ
    2.47
    Sequ
    2.05
     sequencing
    1.84
     sequest
    1.69
    sequence
    1.37
     sequential
    1.32
    seq
    1.17
     Sequence
    1.11
    Activations Density 0.031%

    No Known Activations