INDEX

Explanations

phrases attributing authorship or responsibility

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

co

-0.49

sa

-0.47

all

-0.44

 sent

-0.44

<eos>

-0.44

her

-0.42

ոյ

-0.41

 indu

-0.41

no

-0.40

POSITIVE LOGITS

 Monfieur

1.05

Efq

0.98

 itſelf

0.98

 Jefus

0.94

 Reſ

0.94

UnusedPrivate

0.92

 Theſe

0.92

WebElementEntity

0.92

 doubtnut

0.91

 ſche

0.90

Activations Density 0.000%

phrases attributing authorship or responsibility

No Comments

No Known Activations