INDEX

Explanations

references to software components and licensing terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

jsdelivr

-0.89

mybatisplus

-0.88

 AssemblyCulture

-0.87

principalColumn

-0.85

 beginnetje

-0.84

webElementXpaths

-0.84

enterOuterAlt

-0.83

ItemBackground

-0.82

OGND

-0.81

featureID

-0.80

POSITIVE LOGITS

message

0.67

Message

0.57

 message

0.56

<tbody>

0.53

 Message

0.50

MESSAGE

0.49

↵↵

0.49

↵

0.48

RelativePath

0.47

<tr>

0.47

Activations Density 0.016%

references to software components and licensing terms

No Comments

No Known Activations