INDEX

Explanations

phrases related to willingness or readiness to do something

oai_token-act-pair · gpt-3.5-turbo

the phrase "willing to" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Compass

-0.86

Offline

-0.77

////////////////////////////////

-0.74

_.

-0.73

Facebook

-0.72

ARS

-0.66

 Detected

-0.66

Veh

-0.64

Haunted

-0.63

Wan

-0.63

POSITIVE LOGITS

 accept

1.14

 embrace

1.14

 sacrifice

1.03

 cooperate

1.03

 give

1.02

 abandon

1.00

 tolerate

0.98

 admit

0.96

 undertake

0.96

 sell

0.95

Activations Density 0.078%

phrases related to willingness or readiness to do something

the phrase "willing to" in various contexts

No Comments

No Known Activations