INDEX

Explanations

terms related to trends and patterns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

-0.65

ctos

-0.61

Corporation

-0.60

 anzu

-0.60

 Sheppard

-0.60

 Knowles

-0.59

 Faces

-0.59

 room

-0.59

 Corporation

-0.59

ת

-0.59

POSITIVE LOGITS

 trends

1.26

 Trend

1.12

 Trends

1.12

trends

1.10

Trends

1.09

 trend

1.06

Trend

1.04

 TRENDS

1.04

 raiſ

1.00

trend

0.99

Activations Density 0.126%

terms related to trends and patterns

No Comments

No Known Activations