INDEX

Explanations

keywords related to tips, instructions, tutorials, or advice

oai_token-act-pair · gpt-3.5-turbo

terms related to measurements and metrics in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ö¼

-0.70

Ø§ÙĦ

-0.70

Cola

-0.70

kefeller

-0.70

assian

-0.70

 Himself

-0.70

$.

-0.69

Ò

-0.69

Course

-0.65

FTWARE

-0.64

POSITIVE LOGITS

 refers

0.84

 spoilers

0.77

 aside

0.75

 consists

0.73

 varies

0.71

 âĵĺ

0.71

 translations

0.69

 includes

0.68

huh

0.68

 overview

0.67

Activations Density 0.489%

keywords related to tips, instructions, tutorials, or advice

terms related to measurements and metrics in various contexts

No Comments

No Known Activations