INDEX

Explanations

mentions of political figures and events

oai_token-act-pair · gpt-3.5-turbo

mentions of political figures and events

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

âĹ¼

-0.84

LTD

-0.83

netflix

-0.82

 Mages

-0.79

 Kubrick

-0.78

 DMCA

-0.77

seless

-0.73

REDACTED

-0.73

usercontent

-0.70

ItemTracker

-0.70

POSITIVE LOGITS

 campaigning

1.32

 frontrunner

1.25

 Iowa

1.23

 caucuses

1.22

 stump

1.21

 endorsements

1.20

 polling

1.16

 campaign

1.13

 fundra

1.12

 polls

1.11

Activations Density 0.635%

mentions of political figures and events

mentions of political figures and events

No Comments

No Known Activations