INDEX

Explanations

words associated with inducing or causing various responses and effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

mybatisplus

-0.80

 poveznice

-0.69

 intptr

-0.65

IntoConstraints

-0.62

styleable

-0.62

ReusableCell

-0.59

rimônio

-0.57

 strut

-0.57

;';

-0.57

 listen

-0.57

POSITIVE LOGITS

 provoked

1.26

 provoke

1.22

 triggered

1.22

caused

1.12

 triggering

1.09

 caused

1.08

 induced

1.07

triggered

1.04

trigger

1.04

 Induced

1.02

Activations Density 0.946%

words associated with inducing or causing various responses and effects

No Comments

No Known Activations