INDEX

Explanations

occurrences of past actions and references to previous experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Autoritní

-0.47

("")]

-0.40

 MainAxisSize

-0.38

 spé

-0.37

 ModelExpression

-0.36

JvmStatic

-0.33

 trá

-0.30

 amplio

-0.30

 heller

-0.29

 encore

-0.28

POSITIVE LOGITS

MessageTagHelper

0.65

 ceased

0.58

 EconPapers

0.57

 withdrew

0.54

 abruptly

0.53

 rescin

0.53

 ceasing

0.51

 cease

0.51

rogram

0.50

StructEnd

0.50

Activations Density 0.585%

occurrences of past actions and references to previous experiences

No Comments

No Known Activations