INDEX

Explanations

words related to showing or displaying something

oai_token-act-pair · gpt-3.5-turbo

the occurrence of the word "showing" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ryu

-0.64

 Â·

-0.61

ictionary

-0.61

complex

-0.60

ire

-0.58

irs

-0.58

orneys

-0.57

scribe

-0.56

govern

-0.56

soc

-0.56

POSITIVE LOGITS

 showing

3.44

 demonstrating

2.21

 displaying

2.14

 showcasing

1.98

 illustrating

1.95

 exhibiting

1.86

 depicting

1.78

 proving

1.78

shows

1.72

 indicating

1.71

Activations Density 0.017%

words related to showing or displaying something

the occurrence of the word "showing" in various contexts

No Comments

No Known Activations