INDEX

Explanations

occurrences of programming language syntax related to function or method definitions and declarations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ⓧ

-1.02

 EconPapers

-0.93

 jadx

-0.77

PullParser

-0.72

tanleria

-0.71

basicConfig

-0.69

 Watertown

-0.69

 franceses

-0.68

енча

-0.67

 acoper

-0.66

POSITIVE LOGITS

(__

1.88

(__

1.00

Ārējās

0.70

mush

0.62

 оригіналу

0.61

ونه

0.58

[__

0.58

corpor

0.58

)__

0.57

 getItem

0.57

Activations Density 0.010%

occurrences of programming language syntax related to function or method definitions and declarations

No Comments

No Known Activations