INDEX

Explanations

adjectives that express vague or inconsistent qualities

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

protoimpl

-0.64

PyExc

-0.56

 OFDb

-0.56

parsedMessage

-0.54

 jadx

-0.51

ConstraintMaker

-0.50

TintMode

-0.49

 tilf

-0.47

 LIBR

-0.47

はじめに

-0.47

POSITIVE LOGITS

 itself

0.61

 الرياضيه

0.60

 ebenfalls

0.56

ArgsConstructor

0.55

いる

0.54

+'</

0.54

itself

0.54

allen

0.53

btw

0.53

CloseOperation

0.53

Activations Density 0.893%

adjectives that express vague or inconsistent qualities

No Comments

No Known Activations