INDEX

Explanations

phrases that indicate comparisons and evaluations

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

followed by punctuation or prepositions

np_acts-logits-general · gemini-2.0-flash

hyphenated words and phrases

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

tagext

-0.89

]--;

-0.86

 AssemblyTitle

-0.83

?}",

-0.82

ChildScrollView

-0.80

'},

-0.79

"]}

-0.78

"],

-0.78

SBATCH

-0.77

iedler

-0.76

POSITIVE LOGITS

2.58

-$

1.02

-'

1.00

‑

0.99

-\

0.94

‐

0.94

-...

0.91

-(

0.90

-%

0.85

®-

0.82

Activations Density 0.431%

phrases that indicate comparisons and evaluations

followed by punctuation or prepositions

hyphenated words and phrases

No Comments

No Known Activations