INDEX

Explanations

keywords related to specific objects or elements mentioned in a sentence

oai_token-act-pair · gpt-3.5-turbo

technical or scientific terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

veyard

-0.65

AHL

-0.61

USL

-0.59

 Lans

-0.58

Byr

-0.57

 Dire

-0.57

 Moff

-0.56

 Palest

-0.56

 Haas

-0.56

 ferment

-0.55

POSITIVE LOGITS

axter

0.73

BuyableInstoreAndOnline

0.70

EVA

0.67

alde

0.66

pron

0.62

Oracle

0.62

rican

0.61

wana

0.59

eva

0.59

ourt

0.59

Activations Density 0.481%

keywords related to specific objects or elements mentioned in a sentence

technical or scientific terminology

No Comments

No Known Activations