INDEX

Explanations

references to alignment or agreement in discussions or results

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TestClass

-0.79

lorin

-0.78

knex

-0.78

laca

-0.76

VM

-0.76

EIS

-0.76

 FormsModule

-0.73

 fhould

-0.72

claves

-0.70

 noDo

-0.70

POSITIVE LOGITS

 according

1.64

according

1.60

 According

1.50

According

1.47

 accordance

1.22

 ACCORD

1.09

 متعلقه

1.01

 pursuant

0.99

ording

0.84

 selon

0.82

Activations Density 0.047%

references to alignment or agreement in discussions or results

No Comments

No Known Activations