© 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. 0-RES-JB
    11. 22371
    Prev
    Next
    INDEX
    Explanations

    phrases related to preparation or readiness

    oai_token-act-pair · gpt-3.5-turbo

    the word "prepare" in various contexts related to readiness or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bugs
    -0.70
     Gamergate
    -0.68
     Fem
    -0.59
     Gay
    -0.59
    îĢ
    -0.58
    vo
    -0.57
     Monkey
    -0.57
     Lives
    -0.57
     elephant
    -0.55
    imity
    -0.55
    POSITIVE LOGITS
     prepare
    3.59
     prepares
    2.41
     Prepare
    2.14
     prepared
    2.07
     preparation
    2.02
     preparing
    1.96
    prep
    1.89
     preparations
    1.74
    Prep
    1.61
     Prepar
    1.43
    Activations Density 0.021%

    No Known Activations