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. 11-RES-JB
    6. 8393
    Prev
    Next
    INDEX
    Explanations

    phrases related to self-reflection and personal growth

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal identity and self-reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĥª
    -0.64
    adelphia
    -0.60
    ĸļ
    -0.59
    }}}
    -0.57
    ="#
    -0.55
    ItemTracker
    -0.55
    _-_
    -0.55
    ãħĭãħĭ
    -0.55
    elvet
    -0.54
    ãĤ¦ãĤ¹
    -0.54
    POSITIVE LOGITS
     my
    1.91
     I
    1.89
     myself
    1.65
     me
    1.41
    I
    1.38
     mine
    1.34
     MY
    1.33
     My
    1.31
    my
    1.29
    My
    1.25
    Activations Density 1.643%

    No Known Activations