INDEX

Explanations

phrases indicating causation

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate causation or consequence

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

nets

-0.71

isable

-0.69

arge

-0.68

ensical

-0.66

pse

-0.62

ccording

-0.61

gee

-0.60

©¶æ¥µ

-0.60

ribes

-0.60

front

-0.59

POSITIVE LOGITS

 sheer

0.84

 course

0.76

âĶĢâĶĢâĶĢâĶĢ

0.72

 precaution

0.69

 their

0.64

 inexper

0.64

 luck

0.64

 sudden

0.60

 exhaustion

0.59

VERTIS

0.59

Activations Density 0.070%

phrases indicating causation

phrases that indicate causation or consequence

No Known Activations