© 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. 2-RES-JB
    11. 1331
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the concept of "shortening"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reducing duration or length

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rd
    -0.74
    Gener
    -0.72
    Ro
    -0.70
    NG
    -0.68
    DW
    -0.68
    ILLE
    -0.67
    Detect
    -0.67
    fw
    -0.67
    Fight
    -0.66
     Helpful
    -0.66
    POSITIVE LOGITS
     shortest
    1.05
     shorter
    0.97
     shortened
    0.88
    short
    0.86
     shorten
    0.80
    thens
    0.79
     leng
    0.79
    ftime
    0.78
     mosqu
    0.78
     short
    0.77
    Activations Density 0.012%

    No Known Activations