INDEX

Explanations

explicit mentions of specific events or procedures

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ugeot

-0.92

 FormsModule

-0.85

Rhestr

-0.81

$_"

-0.78

LLocation

-0.77

mybatisplus

-0.77

 BoxFit

-0.76

 FetchType

-0.74

 createSprite

-0.72

ruptedException

-0.72

POSITIVE LOGITS

↵↵

2.00

↵↵↵

1.49

↵↵↵↵

1.41

↵↵↵↵↵

1.36

↵

1.34

<h2>

1.30

<eos>

1.29

↵↵↵↵↵↵

1.26

[toxicity=0]

1.16

<blockquote>

1.15

Activations Density 0.937%

explicit mentions of specific events or procedures

No Comments

No Known Activations