INDEX

Explanations

references to specific political figures or figures related to politics

oai_token-act-pair · gpt-3.5-turbo

mentions of political figures, particularly during discussions of their actions and controversies

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

actionDate

-0.74

lehem

-0.70

DAQ

-0.69

 Mandatory

-0.65

sembly

-0.62

 Mehran

-0.61

!/

-0.61

 Artemis

-0.61

ammy

-0.61

Redd

-0.60

POSITIVE LOGITS

 himself

1.13

's

0.95

 aides

0.93

 Himself

0.88

 swore

0.86

 spends

0.85

 prefers

0.84

 complains

0.82

 believes

0.80

 knows

0.79

Activations Density 0.225%

references to specific political figures or figures related to politics

mentions of political figures, particularly during discussions of their actions and controversies

No Comments

No Known Activations