INDEX

Explanations

references to political figures and controversial statements

oai_token-act-pair · gpt-3.5-turbo

phrases related to media manipulation and controversial political actions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Enlarge

-0.84

ellery

-0.83

ktop

-0.83

sson

-0.79

 ÂŃ

-0.77

"}],"

-0.77

 glim

-0.76

rompt

-0.75

 tactile

-0.74

oji

-0.74

POSITIVE LOGITS

 Illuminati

1.33

MSM

1.27

 Satanic

1.20

 Zionist

1.12

 Soros

1.10

 NEVER

1.08

 Wikileaks

1.07

!!!!

1.06

 AMERICA

1.04

 REAL

1.04

Activations Density 2.017%

references to political figures and controversial statements

phrases related to media manipulation and controversial political actions

No Comments

No Known Activations