INDEX

Explanations

references to objects or activities related to a bathroom

oai_token-act-pair · gpt-3.5-turbo

references to baths and bathing-related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

srf

-0.71

seless

-0.66

VEN

-0.64

 deported

-0.62

phis

-0.60

 disparate

-0.60

guided

-0.58

etary

-0.58

 vague

-0.58

xtap

-0.57

POSITIVE LOGITS

tub

1.70

room

1.22

rooms

1.19

robe

1.17

urst

1.15

 baths

1.03

 salts

0.98

bath

0.95

tub

0.94

 ashore

0.93

Activations Density 0.010%

references to objects or activities related to a bathroom

references to baths and bathing-related contexts

No Comments

No Known Activations