INDEX

Explanations

mentions of the word "lower" in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to low or lower levels of measurement or quality

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Pros

-0.68

andise

-0.66

aint

-0.66

ÂłÂłÂłÂłÂłÂłÂłÂł

-0.65

Jew

-0.65

arya

-0.62

YES

-0.61

wip

-0.60

Ze

-0.60

ONSORED

-0.60

POSITIVE LOGITS

case

0.99

 extrem

0.88

 than

0.88

iating

0.86

 inhib

0.85

iation

0.80

down

0.78

jaw

0.76

iated

0.75

 levels

0.75

Activations Density 0.044%

mentions of the word "lower" in various contexts

references to low or lower levels of measurement or quality

No Comments

No Known Activations