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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 4548
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns used in quotes

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "I" in various contexts, indicating a focus on personal statements or self-reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ļéĨĴ
    -0.74
    ienne
    -0.69
    affles
    -0.63
     Papers
    -0.62
    edient
    -0.58
    pires
    -0.57
    ĺħ
    -0.57
     Eleven
    -0.57
     Butter
    -0.56
     Bezos
    -0.56
    POSITIVE LOGITS
    'm
    1.42
    've
    1.31
    'll
    1.14
     guess
    1.10
     suppose
    0.96
    nex
    0.96
    'd
    0.95
     think
    0.92
     gotta
    0.88
    deals
    0.87
    Activations Density 0.255%

    No Known Activations