INDEX

Explanations

themes related to giving up, surrendering, and abandonment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

aal

-0.68

 Messer

-0.62

ostream

-0.61

viewers

-0.60

 oper

-0.58

 UIApplication

-0.54

러

-0.54

saida

-0.54

XV

-0.53

 Oper

-0.53

POSITIVE LOGITS

WriteBarrier

0.95

 abandonné

0.93

 forget

0.91

 abandon

0.91

 FORGET

0.90

 forsake

0.89

Abandon

0.88

AddTagHelper

0.87

 abandonado

0.85

 Abandon

0.84

Activations Density 0.171%

themes related to giving up, surrendering, and abandonment

No Comments

No Known Activations