INDEX

Explanations

the word "deem" along with related verbs, indicating assessments or judgments

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to judgment or evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 scrimmage

-0.78

dayName

-0.69

rero

-0.65

ohyd

-0.64

 Turtle

-0.63

EStreamFrame

-0.63

ROR

-0.63

ozo

-0.62

 Franch

-0.62

okemon

-0.60

POSITIVE LOGITS

phas

1.58

 unfit

1.03

 unworthy

1.01

 worthy

0.97

fit

0.94

 unsu

0.90

 advisable

0.87

 necessary

0.87

 insufficient

0.87

 appropriate

0.86

Activations Density 0.100%

the word "deem" along with related verbs, indicating assessments or judgments

words and phrases related to judgment or evaluation

No Comments

No Known Activations