INDEX

Explanations

references to actions involving the act of shutting something

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "shut" in various contexts related to closure or cessation

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

lihood

-0.77

omething

-0.69

 IMAGES

-0.69

ertodd

-0.69

agher

-0.67

ampton

-0.67

ordan

-0.66

 Occupations

-0.66

 Values

-0.65

 abund

-0.65

POSITIVE LOGITS

tered

1.46

tering

1.28

ters

1.05

tle

1.03

downs

1.03

down

0.99

outs

0.95

 down

0.92

out

0.92

terness

0.87

Activations Density 0.026%

references to actions involving the act of shutting something

occurrences of the word "shut" in various contexts related to closure or cessation

No Comments

No Known Activations