INDEX

Explanations

words related to knowledge, activities, and experiences

oai_token-act-pair · gpt-3.5-turbo

phrases related to knowledge-based activities and consent

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Äĩ

-0.67

Äį

-0.66

 Tycoon

-0.60

anova

-0.60

ciation

-0.60

PF

-0.58

Unix

-0.58

soDeliveryDate

-0.57

orld

-0.56

wagen

-0.56

POSITIVE LOGITS

 Lauder

0.59

 Scholars

0.55

icit

0.54

 cand

0.52

 Occupations

0.51

speech

0.49

iae

0.49

doi

0.49

athering

0.48

Cly

0.47

Activations Density 1.008%

words related to knowledge, activities, and experiences

phrases related to knowledge-based activities and consent

No Comments

No Known Activations