INDEX

Explanations

phrases related to government legislation and political actions

oai_token-act-pair · gpt-3.5-turbo

references to legislative action and political willingness

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

 Vine

-0.75

 dying

-0.73

 wounding

-0.71

interstitial

-0.70

 Dying

-0.69

 ageing

-0.69

washer

-0.69

Aren

-0.66

origin

-0.65

 Dancing

-0.65

POSITIVE LOGITS

 intervene

1.35

 acknowledge

1.24

 acquies

1.22

 relent

1.18

 heed

1.15

 agree

1.13

 capit

1.13

 reconsider

1.12

 approve

1.10

 sanction

1.08

Activations Density 0.399%

phrases related to government legislation and political actions

references to legislative action and political willingness

No Comments

No Known Activations