INDEX

Explanations

mentions of specific events or notable occurrences

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

ugeot

-1.02

Rhestr

-0.92

 FormsModule

-0.89

 createSprite

-0.88

 FetchType

-0.83

cửa

-0.82

ruptedException

-0.81

 snippetHide

-0.77

$_"

-0.77

iffance

-0.77

POSITIVE LOGITS

↵↵

1.86

<h2>

1.35

↵↵↵

1.34

↵

1.29

↵↵↵↵

1.28

<eos>

1.21

↵↵↵↵↵

1.21

<h3>

1.16

<blockquote>

1.10

↵↵↵↵↵↵

1.09

Activations Density 0.969%

mentions of specific events or notable occurrences

No Comments

No Known Activations