INDEX

Explanations

words related to modifications or alterations

oai_token-act-pair · gpt-3.5-turbo

variations of the word "mod" and its derivatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Lauder

-0.68

 Beir

-0.66

 Bucc

-0.65

 Bulldogs

-0.64

 Mata

-0.61

izabeth

-0.61

terday

-0.60

holding

-0.60

velt

-0.58

 begging

-0.57

POSITIVE LOGITS

ulo

1.37

icum

1.34

ifiable

1.30

ded

1.29

ifiers

1.28

ulations

1.28

ifications

1.28

ding

1.26

elled

1.26

ulus

1.26

Activations Density 0.047%

words related to modifications or alterations

variations of the word "mod" and its derivatives

No Comments

No Known Activations