INDEX

Explanations

phrases related to negative impact or destruction

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "ruin" and its implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

leground

-0.74

bors

-0.72

arij

-0.71

duino

-0.69

appa

-0.69

enne

-0.66

heter

-0.66

arnaev

-0.64

gencies

-0.62

rouch

-0.61

POSITIVE LOGITS

 havoc

1.16

ous

0.87

 ruining

0.82

ously

0.82

 spoil

0.79

OUS

0.78

fully

0.77

 Ukrain

0.76

ifully

0.76

nit

0.74

Activations Density 0.028%

phrases related to negative impact or destruction

references to the concept of "ruin" and its implications

No Comments

No Known Activations