© 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. 6294
    Prev
    Next
    INDEX
    Explanations

    phrases related to different states of semi-closure

    oai_token-act-pair · gpt-3.5-turbo

    references to "semi" in various contexts, particularly indicating a partial state or condition

    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
    Protect
    -0.80
     Hopkins
    -0.79
    justice
    -0.74
    shed
    -0.67
    apper
    -0.67
     DEFENSE
    -0.67
    arted
    -0.66
    share
    -0.66
    CAP
    -0.65
    apping
    -0.65
    POSITIVE LOGITS
     semi
    3.42
     Semi
    2.34
     sem
    2.15
     quasi
    1.49
     semif
    1.29
    Sem
    1.23
     pseudo
    1.18
     moderately
    1.12
     quarter
    1.11
     mini
    1.04
    Activations Density 0.019%

    No Known Activations