INDEX

Explanations

proper nouns and named entities

oai_token-act-pair · gpt-3.5-turbo

abbreviations or acronyms related to organizations or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Hayward

-0.63

 Sinclair

-0.61

 Wink

-0.61

bard

-0.60

ffen

-0.60

 Jarrett

-0.59

phrine

-0.59

gy

-0.59

 Hicks

-0.58

ju

-0.58

POSITIVE LOGITS

ANS

1.52

ION

1.09

IAN

1.05

WER

1.03

UAL

0.96

IRD

0.92

ANE

0.91

ICAN

0.91

ANA

0.90

IONS

0.88

Activations Density 0.003%

proper nouns and named entities

abbreviations or acronyms related to organizations or actions

No Comments

No Known Activations