INDEX

Explanations

identifiers and variable names in programming or markup code

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Text within brackets or parentheses

np_acts-logits-general · gemini-2.0-flash

section references

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itſelf

-0.75

 leſs

-0.60

 myſelf

-0.59

 المعيارى

-0.59

RenderAtEndOf

-0.58

-0.57

GEBURTSDATUM

-0.56

 onely

-0.54

 fubject

-0.54

 leaſt

-0.54

POSITIVE LOGITS

 devs

0.44

 xmas

0.43

 Xmas

0.43

Thx

0.40

 Govt

0.36

ppl

0.36

 refs

0.35

 govt

0.35

 Rptr

0.35

Thx

0.35

Activations Density 2.179%

identifiers and variable names in programming or markup code

Text within brackets or parentheses

section references

No Comments

No Known Activations