© 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. 1637
    Prev
    Next
    INDEX
    Explanations

    verbs relating to directing attention or effort towards a specific task or goal

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "focus on" in various contexts

    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
    ©¶æ¥µ
    -0.90
    DragonMagazine
    -0.74
    LI
    -0.74
    notations
    -0.73
    uid
    -0.72
    mpeg
    -0.71
    dayName
    -0.67
    tie
    -0.67
    externalActionCode
    -0.66
    link
    -0.65
    POSITIVE LOGITS
     improving
    0.99
     preserving
    0.93
     maximizing
    0.93
     solving
    0.90
     optimizing
    0.85
     achieving
    0.80
     aesthetics
    0.77
     developing
    0.77
     maintaining
    0.76
     mitigating
    0.75
    Activations Density 0.083%

    No Known Activations