© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 18697
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Mother" with varying intensities

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Mother" and related phrases indicating maternal themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ript
    -0.83
    ramer
    -0.78
    aping
    -0.76
    ahime
    -0.71
    orman
    -0.71
    neum
    -0.69
    ators
    -0.66
    jriwal
    -0.65
    aped
    -0.65
    ickr
    -0.64
    POSITIVE LOGITS
     Teresa
    0.91
     Mother
    0.88
    BRE
    0.81
    Father
    0.79
    Son
    0.79
    hood
    0.79
    Mother
    0.78
    fuck
    0.78
     Daughter
    0.77
     Earth
    0.74
    Activations Density 0.049%

    No Known Activations