INDEX

Explanations

statements or phrases that indicate dependence or reliance on previous information or findings

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

"Based on"

np_acts-logits-general · gemini-2.0-flash

based on and its degree

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

bcryptjs

-0.86

MLLoader

-0.83

WriteTagHelper

-0.73

 MotionEvent

-0.72

 otomatig

-0.69

LabelTagHelper

-0.66

OrNil

-0.66

 useAuth

-0.66

ătoare

-0.66

SourceChecksum

-0.65

POSITIVE LOGITS

 upon

0.92

on

0.91

 largely

0.77

 partly

0.77

 solely

0.75

 primarily

0.67

off

0.67

 mainly

0.64

 purely

0.62

 partially

0.62

Activations Density 0.114%

statements or phrases that indicate dependence or reliance on previous information or findings

"Based on"

based on and its degree

No Comments

No Known Activations