INDEX

Explanations

words containing the sequence "rom" preceded by a digit

oai_token-act-pair · gpt-3.5-turbo

references to the word "rom" in different contexts, likely indicating a focus on romance or romantic themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Rapids

-0.69

 threshold

-0.66

 Jackets

-0.65

 reminders

-0.64

 fide

-0.63

 Padres

-0.61

 Reserve

-0.61

Notes

-0.60

 haste

-0.60

 caveat

-0.59

POSITIVE LOGITS

antic

1.26

ecast

1.21

ancers

1.16

agnetic

1.11

astery

1.10

antically

1.05

antics

1.04

ancer

1.00

atic

0.98

edy

0.96

Activations Density 0.019%

words containing the sequence "rom" preceded by a digit

references to the word "rom" in different contexts, likely indicating a focus on romance or romantic themes

No Comments

No Known Activations