INDEX

Explanations

phrases indicating a tendency or inclination to do something

oai_token-act-pair · gpt-3.5-turbo

the use of the word "tend" and its variations

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

listed

-0.68

 Chronicle

-0.67

hello

-0.67

Letter

-0.65

prints

-0.64

terday

-0.64

irez

-0.64

planet

-0.63

specified

-0.63

opens

-0.62

POSITIVE LOGITS

 stick

1.03

 rely

0.98

 accumulate

0.97

 resemble

0.94

 attract

0.91

 avoid

0.90

 settle

0.90

 behave

0.89

 lose

0.88

eat

0.88

Activations Density 0.065%

phrases indicating a tendency or inclination to do something

the use of the word "tend" and its variations

No Comments

No Known Activations