INDEX

Explanations

instances of the word "induced" and related forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ConstraintMaker

-0.93

 мәкал

-0.57

makeConstraints

-0.57

ivable

-0.56

ateness

-0.55

 Offensive

-0.55

WindowConstants

-0.55

 roba

-0.54

 hedging

-0.53

 Baus

-0.53

POSITIVE LOGITS

Plugin

0.78

plugins

0.70

 induce

0.69

 commission

0.64

Plugins

0.61

 propOrder

0.61

 order

0.61

 Commission

0.59

 inducing

0.58

induced

0.58

Activations Density 0.162%

instances of the word "induced" and related forms

No Comments

No Known Activations