INDEX

Explanations

personal pronouns indicating ownership or involvement

oai_token-act-pair · gpt-3.5-turbo

references to personal pronouns and their usage in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

except

-0.69

clusively

-0.68

COMPLE

-0.60

zero

-0.60

 instantaneous

-0.59

 unanimous

-0.59

 anymore

-0.59

aza

-0.58

 dime

-0.57

 EVERY

-0.57

POSITIVE LOGITS

 might

2.05

might

2.04

may

1.93

may

1.62

 Might

1.54

maybe

1.54

perhaps

1.46

 maybe

1.44

 could

1.43

MAY

1.43

Activations Density 0.954%

personal pronouns indicating ownership or involvement

references to personal pronouns and their usage in various contexts

No Comments

No Known Activations