INDEX

Explanations

phrases related to comparison between things or concepts

oai_token-act-pair · gpt-3.5-turbo

comparisons or evaluations related to worth and significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

pora

-0.63

oun

-0.59

othal

-0.59

ioxide

-0.57

 unfocusedRange

-0.54

 specifically

-0.54

utra

-0.51

 clearly

-0.50

zik

-0.49

 differently

-0.49

POSITIVE LOGITS

 imaginable

0.57

ERROR

0.51

EST

0.51

depending

0.51

é¾įå

0.49

BUR

0.48

*.

0.48

LECT

0.48

 WARRANT

0.48

enance

0.46

Activations Density 1.004%

phrases related to comparison between things or concepts

comparisons or evaluations related to worth and significance

No Comments

No Known Activations