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. 12608
    Prev
    Next
    INDEX
    Explanations

    contractions or possessive forms involving the apostrophe followed by 'in'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the apostrophe being used in dialogue or contractions

    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
    irez
    -0.81
    rendered
    -0.79
    arer
    -0.78
    ĻĤ
    -0.76
    icz
    -0.76
    uj
    -0.76
    agos
    -0.73
    ¨
    -0.72
    ihar
    -0.71
    ¿½
    -0.68
    POSITIVE LOGITS
     fashioned
    0.80
    Malley
    0.74
    eous
    0.71
     Bastard
    0.68
     Chosen
    0.68
    WOOD
    0.64
     Solitaire
    0.64
     Syndrome
    0.63
     Plenty
    0.63
     Mama
    0.62
    Activations Density 0.017%

    No Known Activations