INDEX

Explanations

terms related to foundational concepts or principles 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Kitz

-0.80

 espelho

-0.79

 Marconi

-0.78

-0.74

 Kości

-0.73

 diagonals

-0.73

 Colla

-0.73

 Roach

-0.72

 roxo

-0.71

 meridian

-0.71

POSITIVE LOGITS

fillment

0.99

FUL

0.97

FUL

0.90

ful

0.82

 Fulfillment

0.82

 fulfillment

0.81

Fundamental

0.77

 fulfill

0.77

 Fundamental

0.76

 fulfills

0.74

Activations Density 0.124%

terms related to foundational concepts or principles in various contexts

No Comments

No Known Activations