INDEX

Explanations

references to previous discussions or articles within the text

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

"in" followed by a noun phrase

np_acts-logits-general · gemini-2.0-flash

in prior references

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 MonoBehaviour

-0.71

PointerException

-0.63

AnimationsModule

-0.58

 venons

-0.57

 FetchType

-0.56

findpost

-0.56

fjspx

-0.55

 Meksiku

-0.54

]-->

-0.54

 للمعارف

-0.54

POSITIVE LOGITS

 article

0.58

AndEndTag

0.57

 recent

0.53

 articles

0.50

our

0.50

 lectures

0.49

RegressionTest

0.48

 Brief

0.47

 tölt

0.45

 lecture

0.45

Activations Density 0.487%

references to previous discussions or articles within the text

"in" followed by a noun phrase

in prior references

No Comments

No Known Activations