INDEX

Explanations

imports and document-related keywords in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

principalColumn

-0.96

 Audiodateien

-0.86

حياته

-0.82

FormTagHelper

-0.79

ArgsConstructor

-0.79

ByPrimaryKey

-0.77

SBATCH

-0.72

Demografía

-0.72

prisma

-0.72

InvalidProtocol

-0.71

POSITIVE LOGITS

awt

1.46

addGroup

0.61

ästi

0.54

RequestMapping

0.52

izr

0.51

 androidx

0.49

 așa

0.48

izumi

0.47

 Voyez

0.46

 utafitiHapana

0.45

Activations Density 0.016%

imports and document-related keywords in code

No Comments

No Known Activations