INDEX

Explanations

words or phrases enclosed in quotation marks

oai_token-act-pair · gpt-3.5-turbo

phrases that are cited or quoted, often marked by quotation marks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

pse

-0.78

 tremend

-0.77

 hooks

-0.76

 throne

-0.75

 destro

-0.75

 hatch

-0.74

 refunds

-0.72

 rall

-0.71

 reside

-0.69

 vents

-0.68

POSITIVE LOGITS

false

1.13

true

1.09

pure

1.04

mega

1.03

smart

1.02

Operation

1.01

prem

1.00

cal

0.99

personal

0.99

ordinary

0.97

Activations Density 0.071%

words or phrases enclosed in quotation marks

phrases that are cited or quoted, often marked by quotation marks

No Comments

No Known Activations