INDEX

Explanations

references to HTML and DOM elements

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

The token "element"

np_acts-logits-general · gemini-2.0-flash

element references

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

shadowRadius

-0.66

sizeCache

-0.64

parsedMessage

-0.58

ClInclude

-0.55

estimating

-0.53

Viited

-0.52

 Audiodateien

-0.50

verifyException

-0.50

WriteBarrier

-0.50

 GenerationType

-0.50

POSITIVE LOGITS

wise

0.69

ally

0.63

minecraftforge

0.57

alist

0.56

 composing

0.55

 censi

0.53

ALLY

0.53

Wise

0.53

alami

0.52

صر

0.52

Activations Density 0.098%

references to HTML and DOM elements

The token "element"

element references

No Comments

No Known Activations