INDEX

Explanations

phrases related to the concept of well-being

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a strong negative or disapproving sentiment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Phi

-0.81

 beads

-0.72

 TAMADRA

-0.72

 Compass

-0.71

 Slide

-0.70

 Bravo

-0.67

 Shuttle

-0.66

 Osiris

-0.65

 Tags

-0.65

 Midnight

-0.65

POSITIVE LOGITS

known

1.22

enough

1.21

established

1.18

respected

1.16

connected

1.16

defined

1.16

placed

1.16

earned

1.12

equipped

1.11

informed

1.11

Activations Density 0.041%

phrases related to the concept of well-being

phrases that indicate a strong negative or disapproving sentiment

No Comments

No Known Activations