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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 5651
    Prev
    Next
    INDEX
    Explanations

    instances where the person is describing something they have done or realized

    oai_token-act-pair · gpt-3.5-turbo

    the repeated usage of the phrase "I have" to indicate personal experiences or ownership

    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
     Apart
    -0.70
    urden
    -0.70
     Allied
    -0.67
    artney
    -0.60
     strand
    -0.60
     precursor
    -0.59
    ourgeois
    -0.59
    earable
    -0.58
     sidelines
    -0.57
     Kitt
    -0.57
    POSITIVE LOGITS
     been
    1.12
    been
    1.06
     Been
    0.84
     gotten
    0.83
     heard
    0.83
    always
    0.82
     personally
    0.82
    ©¶æ
    0.81
     always
    0.80
    ļé
    0.80
    Activations Density 0.149%

    No Known Activations