INDEX

Explanations

software or programming language-related terms, specifically related to versions or features

oai_token-act-pair · gpt-3.5-turbo

references to "ES" and related content

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

ichick

-0.86

olulu

-0.78

abwe

-0.77

selage

-0.72

zzle

-0.70

ãĥ£

-0.70

ãĥĥãĥĪ

-0.67

vertising

-0.65

iosity

-0.65

ificent

-0.64

POSITIVE LOGITS

TERN

1.33

IGH

1.15

SAY

1.08

FIN

1.07

PORT

1.04

TA

1.03

SE

1.03

ENS

1.03

CENT

1.01

BUG

1.00

Activations Density 0.025%

software or programming language-related terms, specifically related to versions or features

references to "ES" and related content

No Comments

No Known Activations