INDEX

Explanations

references to "post" 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 @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Мексичка

-1.19

 متعلقه

-1.18

migrationBuilder

-1.17



-1.12

 cherchés

-1.11

 XCTest

-1.00

SerializedSize

-0.97

continence

-0.97

__':

-0.97

 HasFactory

-0.95

POSITIVE LOGITS

 Post

1.93

Post

1.90

 POST

1.85

post

1.84

 post

1.73

POST

1.72

 posts

1.57

 Posts

1.56

Posts

1.48

posts

1.39

Activations Density 0.066%

references to "post" in various contexts

No Comments

No Known Activations