© 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. 6-RES-JB
    11. 2629
    Prev
    Next
    INDEX
    Explanations

    words related to the ages of children

    oai_token-act-pair · gpt-3.5-turbo

    mentions of age ranges for children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shapiro
    -0.74
     Mechdragon
    -0.72
     Duffy
    -0.71
     Neville
    -0.67
    ļéĨĴ
    -0.67
     charms
    -0.66
     Blizzard
    -0.66
    Ùİ
    -0.65
     McGu
    -0.64
     alle
    -0.64
    POSITIVE LOGITS
    sized
    1.12
    prison
    1.07
    interstitial
    1.02
    appointed
    1.02
    definition
    1.02
    month
    0.97
    length
    0.96
    iversary
    0.96
    ago
    0.95
    terms
    0.94
    Activations Density 0.045%

    No Known Activations