INDEX

Explanations

phrases related to policies, actions, or decisions

oai_token-act-pair · gpt-3.5-turbo

phrases that use the word "has" to denote possession or a state of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

eem

-0.67

 observing

-0.60

 behold

-0.60

atically

-0.59

bart

-0.59

 Penal

-0.59

 typing

-0.58

 Model

-0.56

Interested

-0.56

 writing

-0.55

POSITIVE LOGITS

 been

1.45

 undergone

1.19

 become

1.16

 begun

1.13

 arisen

1.10

been

1.09

 gotten

1.02

 risen

1.00

 Been

0.96

 gone

0.96

Activations Density 0.261%

phrases related to policies, actions, or decisions

phrases that use the word "has" to denote possession or a state of being

No Comments

No Known Activations