INDEX

Explanations

verbs indicating change or progression, especially in a positive context

oai_token-act-pair · gpt-3.5-turbo

repeated phrases that indicate ongoing or continuous actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Penal

-0.66

 observing

-0.64

 performing

-0.63

Interested

-0.61

 behold

-0.61

atin

-0.59

 administering

-0.59

 submitting

-0.58

 cursing

-0.58

 recall

-0.57

POSITIVE LOGITS

 been

1.50

been

1.27

 become

1.21

 arisen

1.18

 Been

1.11

 resulted

1.11

 undergone

1.11

 begun

1.10

 gotten

1.03

 risen

1.00

Activations Density 0.254%

verbs indicating change or progression, especially in a positive context

repeated phrases that indicate ongoing or continuous actions or states

No Comments

No Known Activations