© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 6666
    Prev
    Next
    INDEX
    Explanations

    phrases related to achieving success or hitting a positive outcome

    oai_token-act-pair · gpt-3.5-turbo

    idiomatic expressions involving "hit" that indicate success or achievement

    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
    gio
    -0.71
    umn
    -0.65
    LC
    -0.62
    tering
    -0.61
    lege
    -0.61
    aying
    -0.60
    igation
    -0.60
    urdue
    -0.60
     formed
    -0.60
    Panel
    -0.59
    POSITIVE LOGITS
     stride
    1.25
     brakes
    1.09
     snag
    1.05
     nail
    0.98
     reset
    0.91
     pavement
    0.90
     itch
    0.89
     accelerator
    0.88
     pause
    0.88
     button
    0.87
    Activations Density 0.122%

    No Known Activations