INDEX

Explanations

words related to expressions and conceptual connections in language

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ImageContext

-0.67

)++;

-0.58

RegistryLite

-0.57

énéral

-0.56

 diverti

-0.55

antiate

-0.54

 varsa

-0.53

 brill

-0.53

kesha

-0.52

≌

-0.52

POSITIVE LOGITS

gdx

0.79

InjectAttribute

0.76

findpost

0.76

 CreateTagHelper

0.75

jā

0.71

().__

0.69

 كومونز

0.68

AsUp

0.68

 跳转至

0.66

 MainAxisSize

0.66

Activations Density 0.120%

words related to expressions and conceptual connections in language

No Comments

No Known Activations