INDEX

Explanations

specific locations or entities mentioned in a political context

oai_token-act-pair · gpt-3.5-turbo

references to political figures and their interactions with specific communities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ĸļ

-0.83

 catalogue

-0.70

 Grimoire

-0.69

 Guinness

-0.65

BMC

-0.64

 decomp

-0.63

 Dart

-0.62

 Clockwork

-0.62

odder

-0.62

 analys

-0.60

POSITIVE LOGITS

 Cosponsors

1.11

 Corker

1.02

 billionaire

0.89

Trump

0.83

Republican

0.81

Republicans

0.81

TRUMP

0.80

hillary

0.77

 boycot

0.77

 lobbyists

0.76

Activations Density 0.733%

specific locations or entities mentioned in a political context

references to political figures and their interactions with specific communities

No Comments

No Known Activations