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. 7-RES-JB
    6. 24258
    Prev
    Next
    INDEX
    Explanations

    personal statements or opinions starting with "I"

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express personal identity or self-reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tnc
    -0.68
    tains
    -0.66
     indistinguishable
    -0.57
     Rockefeller
    -0.57
     Gap
    -0.55
     Reverse
    -0.54
    groupon
    -0.54
     excess
    -0.54
    pires
    -0.53
     Philipp
    -0.53
    POSITIVE LOGITS
    'm
    1.45
    've
    1.31
     dunno
    1.22
    'll
    1.22
     suppose
    1.15
    'd
    1.06
    nex
    1.02
     guess
    1.01
    WI
    1.00
     mean
    0.97
    Activations Density 0.233%

    No Known Activations