INDEX

Explanations

words related to confrontation and its consequences

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

 Becomes

-0.65

 Become

-0.62

MessageTagHelper

-0.61

Become

-0.60

 survives

-0.60

 thrives

-0.59

 bénéfic

-0.58

 resists

-0.58

ViewFeatures

-0.58

Stay

-0.58

POSITIVE LOGITS

 trigger

0.64

 propOrder

0.63

 cause

0.59

CloseOperation

0.57

 kick

0.54

alec

0.51

 betweenstory

0.51

setViewportView

0.51

::~

0.51

artifactId

0.50

Activations Density 0.677%

words related to confrontation and its consequences

No Comments

No Known Activations