INDEX

Explanations

terms related to names or specific terms in a technical context

oai_token-act-pair · gpt-3.5-turbo

names or nouns related to people and places

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

DERR

-0.70

JUST

-0.67

OTAL

-0.64

conserv

-0.62

GGGGGGGG

-0.61

thora

-0.61

lest

-0.61

raped

-0.60

 THESE

-0.60

å¤©

-0.59

POSITIVE LOGITS

 hybrids

0.79

 alike

0.79

 hybrid

0.77

heid

0.71

 complexes

0.65

ipeg

0.64

byter

0.63

£ı

0.60

erker

0.59

 syndrome

0.59

Activations Density 0.388%

terms related to names or specific terms in a technical context

names or nouns related to people and places

No Comments

No Known Activations