INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

words and elements related to architecture and structural components

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

Negative Logits

houses

-0.71

ramer

-0.67

ufact

-0.66

WARD

-0.65

oso

-0.64

ndra

-0.64

thens

-0.63

owship

-0.63

akeru

-0.63

ghai

-0.63

POSITIVE LOGITS

ishops

0.77

çĶ°

0.73

 Skydragon

0.68

Ĩ

0.68

ãĥĨãĤ£

0.67

ulhu

0.65

ļ

0.64

agos

0.64

å¥³

0.63

å°Ĩ

0.63

Activations Density 0.225%

proper nouns

words and elements related to architecture and structural components

No Known Activations