INDEX

Explanations

pieces of structured data or code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

Configurator

-0.55

configure

-0.49

Configured

-0.49

ImGui

-0.47

 Swain

-0.46

LEADING

-0.46

TEN

-0.44

APT

-0.44

 bedo

-0.43

 gars

-0.43

POSITIVE LOGITS

ViewGroup

1.77

 mergeFrom

1.41

ButtonStyle

0.98

StoryboardSegue

0.95

InjectAttribute

0.94

SerializedSize

0.94

 חיצוניים

0.93

AndroidJUnit

0.89

BeginContext

0.87

 EClass

0.84

Activations Density 0.001%

pieces of structured data or code

No Comments

No Known Activations