INDEX

Explanations

mentions of governmental actions or decisions, especially regarding regulations or bans

oai_token-act-pair · gpt-3.5-turbo

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

 solitude

-0.74

 Lives

-0.74

 wander

-0.72

 Conversation

-0.69

opian

-0.68

INTER

-0.66

Ô

-0.65

 Dying

-0.65

Translation

-0.65

geries

-0.65

POSITIVE LOGITS

 announced

1.47

 rescind

1.36

 revoked

1.31

announced

1.20

 unanimously

1.20

 issued

1.18

 unveiled

1.18

 postponed

1.18

 formally

1.16

 reinstated

1.16

Activations Density 0.319%

mentions of governmental actions or decisions, especially regarding regulations or bans

No Comments

No Known Activations