INDEX

Explanations

factors influencing decisions and behaviors, particularly in political or organizational contexts

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

"For" followed by a justification/reason

np_acts-logits-general · gemini-2.0-flash

for assorted reasons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 '\\;'

-0.69

########.

-0.66

 kaarangay

-0.65

parsedMessage

-0.65

TintMode

-0.61

 مشين

-0.61

dafx

-0.61

tagHelperRunner

-0.58

 wireType

-0.58

ItemBackground

-0.58

POSITIVE LOGITS

 logistical

1.07

 economic

1.06

 reasons

1.04

 practical

1.00

 technical

0.99

 pragmatic

0.93

 ethical

0.93

 practicality

0.91

 ideological

0.88

 Reasons

0.88

Activations Density 0.718%

factors influencing decisions and behaviors, particularly in political or organizational contexts

"For" followed by a justification/reason

for assorted reasons

No Comments

No Known Activations