INDEX

Explanations

terms related to optical and genetic topics

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

preceding "nerve," "vision," or related sensory terms

np_acts-logits-general · gemini-2.0-flash

technical prefixes

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

webElementXpaths

-0.80

ergies

-0.70

 jLabel

-0.68

onora

-0.67

tvguidetime

-0.67

houses

-0.66

 виправивши

-0.66

RTEX

-0.63

Życiorys

-0.62

 Walkover

-0.62

POSITIVE LOGITS

ally

1.69

ALLY

1.37

all

0.85

amente

0.82

idad

0.76

als

0.76

hes

0.71

idal

0.70

zne

0.69

zny

0.69

Activations Density 0.655%

terms related to optical and genetic topics

preceding "nerve," "vision," or related sensory terms

technical prefixes

No Comments

No Known Activations