INDEX

Explanations

occurrences of the word "a" in various contexts

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CopyWith

-0.47

kio

-0.47

ScopeManager

-0.46

 biggest

-0.45

sssss

-0.45

WillAppear

-0.44

 יוצ

-0.44

 الاطلاع

-0.44

 dele

-0.43

kok

-0.42

POSITIVE LOGITS

 '\\;'

0.82

 AspNetCore

0.80

 linkovi

0.78

sizeCache

0.77

 CreateTagHelper

0.77

StoreMessageInfo

0.75

دانشنامهٔ

0.73

 Normdatei

0.72

 MonoBehaviour

0.69

Jeografia

0.69

Activations Density 0.011%

occurrences of the word "a" in various contexts

No Comments

No Known Activations