INDEX

Explanations

references to micro-level concepts in various contexts

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

following "micro"

np_acts-logits-general · gemini-2.0-flash

words starting with micro

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

enderror

-0.76

 JpaRepository

-0.68

PerformLayout

-0.61

 Ause

-0.61

__).

-0.60

ècie

-0.60

}`).

-0.57

Література

-0.54

reurs

-0.53

DispatchToProps

-0.53

POSITIVE LOGITS

 Micro

0.68

Micro

0.67

 micro

0.65

stateProvider

0.64

casm

0.63

 MICRO

0.61

 Mikro

0.60

istoitu

0.59

second

0.58

ähän

0.57

Activations Density 0.114%

references to micro-level concepts in various contexts

following "micro"

words starting with micro

No Comments

No Known Activations