INDEX

Explanations

personal pronouns in second person

oai_token-act-pair · gpt-3.5-turbo

the word "you," indicating a focus on direct address or engagement with the reader

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

iday

-0.67

ipal

-0.64

 hers

-0.63

 Hook

-0.61

kamp

-0.61

 Chap

-0.60

 Hyde

-0.59

hover

-0.59

votes

-0.58

official

-0.58

POSITIVE LOGITS

 guys

1.32

're

1.30

've

1.09

tub

1.01

 guessed

0.90

'll

0.86

 gotta

0.86

 know

0.85

 yourselves

0.84

ngth

0.82

Activations Density 0.221%

personal pronouns in second person

the word "you," indicating a focus on direct address or engagement with the reader

No Comments

No Known Activations