INDEX

Explanations

words related to health, safety, and security

oai_token-act-pair · gpt-3.5-turbo

phrases related to health and safety issues

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

nik

-0.81

hov

-0.79

atari

-0.76

ãĥķãĤ¡

-0.72

ADVERTISEMENT

-0.72

:[

-0.72

hit

-0.71

:(

-0.71

*:

-0.70

ukong

-0.69

POSITIVE LOGITS

 resources

0.87

 consequently

0.82

 wellbeing

0.79

 possibly

0.79

 nurturing

0.79

 palate

0.77

 therefore

0.77

 attendant

0.77

 dignity

0.74

 nurture

0.73

Activations Density 0.497%

words related to health, safety, and security

phrases related to health and safety issues

No Comments

No Known Activations