INDEX

Explanations

phrases related to justification or exoneration

oai_token-act-pair · gpt-3.5-turbo

words related to validation and justification

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

pee

-0.80

atomic

-0.68

pmwiki

-0.68

senal

-0.67

abwe

-0.66

cules

-0.64

 livest

-0.64

parts

-0.63

OPLE

-0.62

cule

-0.62

POSITIVE LOGITS

ictive

1.29

ication

1.21

icated

1.19

ict

1.03

icates

1.02

ications

1.02

 vind

0.99

icator

0.99

iary

0.98

icating

0.96

Activations Density 0.019%

phrases related to justification or exoneration

words related to validation and justification

No Comments

No Known Activations