INDEX

Explanations

phrases or terms that indicate the presence of factors or variables in a context

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

"factor" or "factors"

np_acts-logits-general · gemini-2.0-flash

factor followed by modifier

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

abetes

-0.92

原始内容存档于

-0.76

LIS

-0.75

úsqueda

-0.72

eet

-0.71

ագրություններ

-0.71

 onCreateView

-0.68

 كومونز

-0.68

sslich

-0.67

ếng

-0.65

POSITIVE LOGITS

 Factors

1.19

 factors

1.17

 FACTOR

1.14

 Factor

1.10

factors

1.04

 FACTORS

1.04

Factors

1.01

Factor

1.00

faktor

1.00

actor

0.98

Activations Density 0.130%

phrases or terms that indicate the presence of factors or variables in a context

"factor" or "factors"

factor followed by modifier

No Comments

No Known Activations