INDEX

Explanations

words related to negative events or situations, particularly emphasizing the concept of "worst."

oai_token-act-pair · gpt-3.5-turbo

descriptions of extreme negativity or adverse conditions

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

ynthesis

-0.87

sure

-0.80

ivating

-0.77

uador

-0.77

cript

-0.75

leans

-0.74

trl

-0.74

itialized

-0.72

arya

-0.72

plex

-0.70

POSITIVE LOGITS

 offender

1.11

 offenders

1.08

 nightmare

0.99

 nightmares

0.94

 behaved

0.86

 imaginable

0.83

 atrocities

0.79

 mistake

0.78

 disasters

0.78

Versions

0.76

Activations Density 0.054%

words related to negative events or situations, particularly emphasizing the concept of "worst."

descriptions of extreme negativity or adverse conditions

No Comments

No Known Activations