INDEX

Explanations

intense descriptions or expressions of completeness or totality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

jangkau

-0.71

 Miquel

-0.70

 Kontakte

-0.65

 piety

-0.64

 åren

-0.62

 mussels

-0.59

 respectivement

-0.59

 lungo

-0.58

 heur

-0.58

 sice

-0.58

POSITIVE LOGITS

 totally

1.25

 completely

1.25

 Completely

1.20

 Totally

1.20

Completely

1.13

Totally

1.12

completely

1.04

totally

1.02

 entirely

0.99

benar

0.98

Activations Density 0.104%

intense descriptions or expressions of completeness or totality

No Comments

No Known Activations