INDEX

Explanations

phrases expressing negation or the impossibility of actions or options

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

"can't" or "cannot"

np_acts-logits-general · gemini-2.0-flash

cannot followed by a verb

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

AndEndTag

-0.51

 Opportun

-0.50

 "..\..\..\

-0.50

wohner

-0.48

itorial

-0.47

ThroughAttribute

-0.45

 oportun

-0.45

 volon

-0.45

 IconData

-0.43

Hentet

-0.43

POSITIVE LOGITS

 truly

0.70

truly

0.69

Filmografie

0.65

 unknow

0.64

 POSS

0.64

ViewImports

0.63

 hope

0.63

 typelib

0.61

 blame

0.61

 blamed

0.61

Activations Density 0.236%

phrases expressing negation or the impossibility of actions or options

"can't" or "cannot"

cannot followed by a verb

No Comments

No Known Activations