INDEX

Explanations

words related to direction or positioning

oai_token-act-pair · gpt-3.5-turbo

terms related to orientation and positioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

å¥³

-0.74

soDeliveryDate

-0.73

orde

-0.71

 Mellon

-0.70

asper

-0.68

ãĤ¨ãĥ«

-0.67

enegger

-0.67

UGC

-0.67

KS

-0.66

Interstitial

-0.66

POSITIVE LOGITS

eering

1.25

 orientation

0.95

ational

0.88

xual

0.86

irection

0.83

¥µ

0.77

 toward

0.75

 orient

0.74

ï¸

0.73

itudinal

0.73

Activations Density 0.027%

words related to direction or positioning

terms related to orientation and positioning

No Comments

No Known Activations