© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 7855
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a hypothetical scenario or outcome dependent on a specific condition being met or not

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements and hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     highlight
    -0.59
    interstitial
    -0.58
     Tick
    -0.55
    atile
    -0.55
    è¦ļéĨĴ
    -0.54
     undermines
    -0.54
     amuse
    -0.53
     brink
    -0.52
    Cube
    -0.52
     hilarious
    -0.52
    POSITIVE LOGITS
     stayed
    1.18
     been
    1.17
     waited
    1.13
    been
    1.08
     hadn
    1.06
     remained
    1.06
     gone
    1.05
     existed
    1.03
     gotten
    1.02
     survived
    1.00
    Activations Density 0.076%

    No Known Activations