INDEX

Explanations

years or dates mentioned in events

oai_token-act-pair · gpt-3.5-turbo

specific years associated with events or activities

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

Not in Any Lists

No Comments

Negative Logits

ongh

-0.83

onic

-0.81

lass

-0.79

iously

-0.77

ambers

-0.75

agic

-0.72

umen

-0.72

ious

-0.71

bor

-0.71

ucha

-0.69

POSITIVE LOGITS

å¹

1.01

 Edition

0.88

 onwards

0.84

 edition

0.78

 EDITION

0.77

 Winners

0.75

0.74

 winner

0.71

 Anniversary

0.70

 Masquerade

0.70

Activations Density 0.053%

years or dates mentioned in events

specific years associated with events or activities

No Comments

No Known Activations