INDEX

Explanations

phrases related to disparity

oai_token-act-pair · gpt-3.5-turbo

instances of the word "par" 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ħĭ

-0.94

¥µ

-0.76

doms

-0.72

 customary

-0.71

houses

-0.70

bern

-0.67

bery

-0.66

ĨĴ

-0.65

hiro

-0.62

å¸

-0.62

POSITIVE LOGITS

allel

1.19

liament

1.07

anoia

0.94

pend

0.87

vati

0.87

 ILCS

0.86

par

0.85

imony

0.84

ques

0.81

anthrop

0.81

Activations Density 0.005%

phrases related to disparity

instances of the word "par" in various contexts

No Comments

No Known Activations