INDEX

Explanations

phrases indicating a contrast or comparison between different things

oai_token-act-pair · gpt-3.5-turbo

expressions that indicate disclaimers or qualifications in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 largeDownload

-0.72

Discussion

-0.69

tnc

-0.66

ortment

-0.65

 Networks

-0.61

LOS

-0.60

BUG

-0.60

Condition

-0.60

visor

-0.59

rotein

-0.59

POSITIVE LOGITS

 anymore

1.68

nor

1.49

 slightest

1.29

 necessarily

1.12

 whatsoever

1.04

necess

1.03

 anywhere

1.02

 anything

1.02

yet

1.01

any

0.94

Activations Density 0.847%

phrases indicating a contrast or comparison between different things

expressions that indicate disclaimers or qualifications in statements

No Comments

No Known Activations