© 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. 4-RES-JB
    11. 5100
    Prev
    Next
    INDEX
    Explanations

    references to childhood or being a child

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "kid" and related themes of childhood

    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
    etting
    -0.80
    aukee
    -0.78
    undai
    -0.76
    quarters
    -0.75
    ĺħ
    -0.75
    veyard
    -0.75
    atility
    -0.74
    aeda
    -0.72
    ewater
    -0.72
    ued
    -0.71
    POSITIVE LOGITS
     kid
    0.94
     Icar
    0.89
     Doodle
    0.84
    ishly
    0.81
     Gohan
    0.80
    boy
    0.79
    girl
    0.77
     Mutant
    0.77
    Kid
    0.75
     FANT
    0.74
    Activations Density 0.019%

    No Known Activations