INDEX

Explanations

mentions of programming code and legal or logical "fore/below/following" references

oai_token-act-pair · gemini-2.0-flash

Code and legal documents

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

]='\

-1.00

StoryboardSegue

-1.00

AndEndTag

-0.97

DockStyle

-0.95

tvguidetime

-0.88

 صوتيه

-0.87

makeConstraints

-0.85

 كومونز

-0.84

 onCancelled

-0.84

 intptr

-0.75

POSITIVE LOGITS

 below

0.96

below

0.75

 Below

0.75

Below

0.75

 above

0.72

 abaixo

0.69

 following

0.64

Listed

0.61

above

0.59

<bos>

0.56

Activations Density 0.916%

mentions of programming code and legal or logical "fore/below/following" references

Code and legal documents

No Comments

No Known Activations

mentions of programming code and legal or logical "fore/below/following" references

Code and legal documents

No Comments

No Known Activations