© 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
    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. 17702
    Prev
    Next
    INDEX
    Explanations

    phrases related to childhood memories

    oai_token-act-pair · gpt-3.5-turbo

    references to childhood experiences and memories

    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
    ioxide
    -0.93
    abase
    -0.88
    andum
    -0.78
    rored
    -0.77
    uid
    -0.75
    vy
    -0.72
    aton
    -0.72
    apter
    -0.71
    heading
    -0.70
    qt
    -0.69
    POSITIVE LOGITS
     memories
    1.05
     innocence
    0.99
     leukemia
    0.96
     trauma
    0.93
     adversity
    0.84
     friendships
    0.83
     experiences
    0.82
     dreams
    0.81
     playground
    0.79
     obesity
    0.78
    Activations Density 0.053%

    No Known Activations