INDEX

Explanations

personal pronouns indicating ownership or affiliation

oai_token-act-pair · gpt-3.5-turbo

pronouns related to personal experience and perspective

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

itialized

-0.74

quartered

-0.69

vine

-0.68

cru

-0.67

zyme

-0.66

orously

-0.66

 Monstrous

-0.64

tyard

-0.63

ories

-0.63

ĸļ

-0.63

POSITIVE LOGITS

 sake

0.98

 personally

0.97

 liking

0.91

selves

0.89

 purposes

0.89

self

0.79

 learners

0.77

ummies

0.76

 reasons

0.74

 selves

0.72

Activations Density 0.110%

personal pronouns indicating ownership or affiliation

pronouns related to personal experience and perspective

No Comments

No Known Activations