INDEX

Explanations

terms related to internal and external processes or states

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

 McClure

-0.87

fromCharCode

-0.78

 glutamate

-0.75

 Montrose

-0.74

GrantedAuthority

-0.73

 casado

-0.72

 locust

-0.71

 poética

-0.71

 defaultstate

-0.71

 تضيفلها

-0.70

POSITIVE LOGITS

 Internal

1.22

 internal

1.19

 INTERNAL

1.14

Internal

1.07

internal

1.02

ternal

0.98

INTERNAL

0.91

 internally

0.90

 internas

0.90

nals

0.85

Activations Density 0.097%

terms related to internal and external processes or states

No Comments

No Known Activations