INDEX

Explanations

sequences of numerical indices or identifiers within a technical or programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

بوابة

-0.76

 '\\;'

-0.72

 snippetHide

-0.69

jspx

-0.68

sizeCache

-0.67

enumi

-0.65

StackNavigator

-0.63

webElementGuid

-0.63

 insuffisamment

-0.61

 resourceCulture

-0.60

POSITIVE LOGITS

kow

0.51

}\]

0.45

 casar

0.45

ograft

0.43

 sher

0.43

 amide

0.43

minal

0.42

 Injection

0.42

 forceps

0.42

 Reflective

0.42

Activations Density 1.019%

sequences of numerical indices or identifiers within a technical or programming context

No Comments

No Known Activations