INDEX

Explanations

the word "trigger" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ValueStyle

-0.77

 Shand

-0.76

osoba

-0.74

addView

-0.71

;"></

-0.69

 Doran

-0.69

Più

-0.69

 resourceCulture

-0.68

 Bors

-0.68

POSITIVE LOGITS

 trigger

2.35

 triggers

2.16

 Trigger

2.15

trigger

2.07

 Triggers

2.07

Trigger

2.05

triggers

1.91

 triggered

1.91

 triggering

1.84

Triggers

1.82

Activations Density 0.121%

the word "trigger" in various contexts

No Comments

No Known Activations