INDEX

Explanations

terms associated with influence or impact on various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Majefty

-1.77

 myſelf

-1.75

 doubtnut

-1.74

 purpoſe

-1.71

ſelf

-1.71

Efq

-1.71

 pleaſure

-1.70

 itſelf

-1.66

ſelves

-1.64

 poffible

-1.57

POSITIVE LOGITS

 affecting

1.07

1.00

↵

0.90

0.87

0.86

0.85

The

0.83

0.82

0.81

↵↵

0.80

Activations Density 0.423%

terms associated with influence or impact on various subjects

No Comments

No Known Activations