© 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. 18433
    Prev
    Next
    INDEX
    Explanations

    phrases related to attention to detail or precision

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "carefully" indicating attention to detail or precision

    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
    anon
    -0.89
    Stars
    -0.83
    entity
    -0.76
    hey
    -0.72
    amy
    -0.71
    asta
    -0.69
    adia
    -0.69
    hello
    -0.68
    ANS
    -0.68
    amaz
    -0.68
    POSITIVE LOGITS
     crafted
    1.05
     calibrated
    1.01
     carefully
    1.00
     deline
    0.94
     cultivated
    0.91
     chore
    0.91
     deliber
    0.89
     careful
    0.89
     scrutin
    0.88
     calibr
    0.88
    Activations Density 0.063%

    No Known Activations