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. 6-RES-JB
    6. 12774
    Prev
    Next
    INDEX
    Explanations

    mentions of a personal creation or project

    oai_token-act-pair · gpt-3.5-turbo

    the repeated reference to 'this' 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
    isms
    -0.78
    aws
    -0.78
    ©¶æ¥µ
    -0.76
    ¨
    -0.73
    planes
    -0.72
    ãĤ¹ãĥĪ
    -0.71
    rors
    -0.71
    Ĭ±
    -0.70
    Ľ
    -0.70
    ãĥĥ
    -0.70
    POSITIVE LOGITS
     particular
    0.94
     trope
    0.90
     sucker
    0.86
     newfound
    0.83
     guy
    0.83
     week
    0.82
     information
    0.81
     happen
    0.81
     nifty
    0.79
     latest
    0.79
    Activations Density 0.175%

    No Known Activations