INDEX

Explanations

words related to seduction or sedition

oai_token-act-pair · gpt-3.5-turbo

terms related to sedition or incitement against authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Origin

-0.73

BY

-0.69

Universal

-0.69

SHIP

-0.69

pei

-0.66

 Millennium

-0.66

¶ħ

-0.65

LAT

-0.64

Ign

-0.62

 inaction

-0.62

POSITIVE LOGITS

iments

1.14

uct

1.14

entary

1.13

uctive

1.11

icating

1.02

ibly

1.00

icates

1.00

uces

1.00

ucing

0.98

icated

0.95

Activations Density 0.016%

words related to seduction or sedition

terms related to sedition or incitement against authority

No Comments

No Known Activations