INDEX

Explanations

words indicating possession or existence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Chriftian

-1.00

 ſtate

-0.97

 houſe

-0.95

 myſelf

-0.95

 poffible

-0.90

 purpoſe

-0.90

 againſt

-0.89

 Monfieur

-0.87

 ainfi

-0.86

 themſelves

-0.86

POSITIVE LOGITS

had

1.45

has

1.40

 been

1.31

Has

1.21

HAS

1.17

 have

1.14

1.04

had

1.01

HAD

1.01

Has

1.01

Activations Density 0.479%

words indicating possession or existence

No Comments

No Known Activations