INDEX

Explanations

words related to beverages, specifically coffee

oai_token-act-pair · gpt-3.5-turbo

references to coffee

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

orse

-0.81

ROR

-0.76

oral

-0.70

Against

-0.66

oppable

-0.65

numbered

-0.63

guided

-0.63

 Horizons

-0.63

ewski

-0.63

yss

-0.63

POSITIVE LOGITS

 beans

1.12

 Beans

1.03

 coffee

1.01

 bean

0.99

weed

0.95

 cups

0.94

cup

0.90

 Coffee

0.85

 coff

0.85

 cocoa

0.85

Activations Density 0.013%

words related to beverages, specifically coffee

references to coffee

No Comments

No Known Activations