INDEX

Explanations

proper nouns related to locations or events

oai_token-act-pair · gpt-3.5-turbo

keywords related to notable events, organizations, or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.).

-0.60

*.

-0.60

`.

-0.59

 attRot

-0.59

irlf

-0.59

};

-0.57

>.

-0.56

Eat

-0.56

}.

-0.56

.),

-0.55

POSITIVE LOGITS

 coincides

1.30

 involves

1.27

 coincided

1.23

 varies

1.23

 differs

1.22

 differed

1.20

 depends

1.20

 exceeds

1.14

 constitutes

1.13

 indicates

1.12

Activations Density 0.692%

proper nouns related to locations or events

keywords related to notable events, organizations, or entities

No Comments

No Known Activations