© 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. 3-RES-JB
    11. 12006
    Prev
    Next
    INDEX
    Explanations

    the mention of something being 'ready' or 'prepared'

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words associated with readiness or preparedness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.83
    ãĤ¢ãĥ«
    -0.72
     mund
    -0.70
    otom
    -0.68
    «ĺ
    -0.67
    effic
    -0.65
     denomin
    -0.65
     slightest
    -0.63
    ibli
    -0.62
    ©¶æ
    -0.61
    POSITIVE LOGITS
     Ready
    1.27
    Ready
    1.00
     Dame
    0.81
    wired
    0.81
    eous
    0.77
    itude
    0.75
     Stead
    0.75
     Ammunition
    0.75
     Enough
    0.71
     Sending
    0.69
    Activations Density 0.013%

    No Known Activations