INDEX

Explanations

first-person pronouns followed by verbs of action

oai_token-act-pair · gpt-3.5-turbo

instances of the first-person pronoun "I"

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

Appearances

-0.69

 possession

-0.65

 Plaint

-0.61

Mech

-0.61

rx

-0.60

PF

-0.58

fighting

-0.57

advant

-0.56

auga

-0.55

¿½

-0.54

POSITIVE LOGITS

'm

1.46

 guess

1.21

 figured

1.15

'll

1.15

've

1.14

 decided

1.10

 wondered

1.10

 suppose

1.07

'd

1.06

am

1.01

Activations Density 0.174%

first-person pronouns followed by verbs of action

instances of the first-person pronoun "I"

No Comments

No Known Activations