INDEX

Explanations

sentences related to actions or events happening in a sequence

oai_token-act-pair · gpt-3.5-turbo

repeated instances of the phrase "has" indicating ongoing 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

-0.65

 observing

-0.63

 Penal

-0.62

 typing

-0.61

 administering

-0.60

Interested

-0.60

 behold

-0.60

 performing

-0.58

 territ

-0.56

 Tribe

-0.56

POSITIVE LOGITS

 been

1.54

been

1.29

 become

1.26

 undergone

1.18

 arisen

1.17

 begun

1.12

 Been

1.09

 gotten

1.08

 risen

1.02

 come

1.01

Activations Density 0.264%

sentences related to actions or events happening in a sequence

repeated instances of the phrase "has" indicating ongoing actions or states

No Comments

No Known Activations