INDEX

Explanations

terms related to definitions, categories, and specific classifications

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 AssemblyProduct

-1.01

FieldBuilder

-0.90

 JpaRepository

-0.80

addPreferredGap

-0.72

URLException

-0.70

حياته

-0.69

ValueStyle

-0.69

ukah

-0.64

MemoryWarning

-0.63

UnusedPrivate

-0.63

POSITIVE LOGITS

its

0.74

Its

0.63

Its

0.57

它的

0.57

 mourir

0.51

 esternos

0.48

labelledby

0.46

 répand

0.46

its

0.44

 UserDao

0.43

Activations Density 0.718%

terms related to definitions, categories, and specific classifications

No Comments

No Known Activations