INDEX

Explanations

instances of the word "take" in various contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "take" and its variants in relation to actions or decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

mingham

-0.71

estamp

-0.71

tch

-0.70

rehens

-0.68

FontSize

-0.68

antha

-0.67

Score

-0.64

gian

-0.64

hoff

-0.64

vine

-0.62

POSITIVE LOGITS

 advantage

1.24

 refuge

1.12

 precautions

1.10

 baths

1.08

 shortcuts

1.06

 risks

1.06

 selfies

1.00

 vacations

0.99

 care

0.98

 steps

0.95

Activations Density 0.084%

instances of the word "take" in various contexts

occurrences of the word "take" and its variants in relation to actions or decisions

No Comments

No Known Activations