INDEX

Explanations

second person pronouns indicating individual responsibility or action

oai_token-act-pair · gpt-3.5-turbo

second-person pronouns and directives addressing the reader

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

equality

-0.57

 apocalyptic

-0.55

shore

-0.55

UTC

-0.55

 accompanied

-0.55

amaz

-0.54

Joined

-0.54

 homosexuality

-0.54

 Scor

-0.53

ornia

-0.52

POSITIVE LOGITS

 shouldn

1.20

'll

1.19

may

1.17

 need

1.16

 SHOULD

1.15

 might

1.15

 MUST

1.12

MAY

1.12

 should

1.08

should

1.05

Activations Density 0.389%

second person pronouns indicating individual responsibility or action

second-person pronouns and directives addressing the reader

No Comments

No Known Activations