INDEX

Explanations

phrases related to inconsistencies or disparities

oai_token-act-pair · gpt-3.5-turbo

terms related to discrepancies and disparities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

abad

-0.81

Interstitial

-0.72

ctors

-0.72

ovy

-0.71

atom

-0.71

NetMessage

-0.71

hammad

-0.70

ert

-0.67

trak

-0.67

ges

-0.66

POSITIVE LOGITS

 discrepancy

1.14

 disparity

1.08

 proport

1.05

 discrepancies

1.04

 disproportion

1.03

 ratios

0.94

 disparities

0.93

 imbalance

0.88

 discrep

0.87

 inconsistency

0.85

Activations Density 0.009%

phrases related to inconsistencies or disparities

terms related to discrepancies and disparities

No Comments

No Known Activations