INDEX

Explanations

terms related to ecological concepts and classifications

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

the prefix "eco"

np_acts-logits-general · gemini-2.0-flash

eco prefix compounds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

bootstrapcdn

-0.75

 itſelf

-0.74

 referenties

-0.73

 seems

-0.73

 seemed

-0.72

 Seems

-0.72

apparent

-0.71

Efq

-0.71

 seemingly

-0.71

AnimationsModule

-0.69

POSITIVE LOGITS

eco

0.70

Eco

0.63

ec

0.61

 echo

0.59

 Echo

0.59

Ec

0.54

Ech

0.54

Eck

0.53

ூ

0.52

Cec

0.52

Activations Density 0.095%

terms related to ecological concepts and classifications

the prefix "eco"

eco prefix compounds

No Comments

No Known Activations