INDEX

Explanations

instances of the word "impression."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

^*)

-0.67

eseorang

-0.62

 spirituale

-0.61

 végétal

-0.61

 énergé

-0.59

 vectoriales

-0.58

 "");

-0.58

thschild

-0.58

 fVar

-0.57

 traditionnels

-0.56

POSITIVE LOGITS

 impression

1.22

impression

1.09

 Impression

1.04

 pits

1.01

 impressions

1.00

pit

0.99

pit

0.90

 Pits

0.85

 implications

0.84

pits

0.84

Activations Density 0.083%

instances of the word "impression."

No Comments

No Known Activations