INDEX

Explanations

code-related terms and functions associated with size, length, and shape

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 Yadav

-0.54

cookieParser

-0.51

GHIJKLM

-0.49

 مرئيه

-0.48

hain

-0.48

Vers

-0.47

 contraire

-0.47

denk

-0.47

owe

-0.47

__(/*!

-0.46

POSITIVE LOGITS

ClientSize

0.99

 getItemCount

0.94

 length

0.89

 numberOfRows

0.86

strlen

0.84

 size

0.82

length

0.77

 strlen

0.76

 argc

0.76

 total

0.76

Activations Density 0.307%

code-related terms and functions associated with size, length, and shape

No Comments

No Known Activations