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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-RES-JB
    6. 22765
    Prev
    Next
    INDEX
    Explanations

    words related to concepts of eternity and immortality

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to eternal life and immortality

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

    No Comments

    Negative Logits
    ¶æ
    -0.82
    ANY
    -0.77
    Priv
    -0.76
    Ô
    -0.72
     Cosponsors
    -0.71
    sonian
    -0.71
     Ging
    -0.70
    acus
    -0.69
    NetMessage
    -0.68
    ett
    -0.65
    POSITIVE LOGITS
     vigilance
    0.95
     coil
    0.87
    istically
    0.82
    itable
    0.80
     bliss
    0.78
     soul
    0.76
     reckoning
    0.75
     salvation
    0.74
    ishable
    0.74
    itability
    0.73
    Activations Density 0.022%

    No Known Activations