INDEX

Explanations

instances where the word "nor" is used to express negation or join two phrases

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Economia

-0.52

ChatColor

-0.47

tvb

-0.47

 Imperio

-0.46

Ђ

-0.45

Distancia

-0.45

EmptyString

-0.45

OleDb

-0.45

Schöne

-0.45

WebControls

-0.44

POSITIVE LOGITS

nor

1.02

 shenan

0.96

 🤣🤣

0.93

 gabri

0.91

 unlaw

0.91

 increa

0.91

 !...

0.90

 milf

0.90

 pamph

0.89

 sergio

0.89

Activations Density 0.085%

instances where the word "nor" is used to express negation or join two phrases

No Comments

No Known Activations