INDEX

Explanations

terms related to computational tasks involving differences or deviations

oai_token-act-pair · gpt-3.5-turbo

terms related to difficulty or challenges

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tto

-0.73

PATH

-0.70

CHO

-0.66

 Outer

-0.66

escape

-0.66

VO

-0.65

Demand

-0.64

 Odyssey

-0.63

 Muse

-0.63

OTT

-0.63

POSITIVE LOGITS

icult

1.42

 diff

1.23

iculty

1.22

diff

1.20

 Diff

1.00

eree

0.94

inished

0.94

raction

0.92

racted

0.88

ractive

0.87

Activations Density 0.007%

terms related to computational tasks involving differences or deviations

terms related to difficulty or challenges

No Comments

No Known Activations