INDEX

Explanations

references to political dictators

oai_token-act-pair · gpt-3.5-turbo

references to dictators and dictatorial regimes

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

older

-0.83

awks

-0.83

alle

-0.80

ilk

-0.80

ttp

-0.80

LAN

-0.78

atha

-0.76

Recommend

-0.76

IGH

-0.75

rb

-0.75

POSITIVE LOGITS

 dictator

1.34

 dictatorship

1.16

 dictators

1.00

 nomine

0.89

 regime

0.85

 overth

0.85

 regimes

0.84

 tyrant

0.82

 tyranny

0.82

 overthrow

0.81

Activations Density 0.009%

references to political dictators

references to dictators and dictatorial regimes

No Known Activations