INDEX

Explanations

warnings or negative implications related to actions that can lead to significant negative consequences

oai_token-act-pair · gpt-3.5-turbo

instances of the word "ruin" and its variations indicating negative consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

arij

-0.81

leground

-0.80

duino

-0.80

bors

-0.76

 reluct

-0.71

appa

-0.70

soType

-0.68

rict

-0.68

rouch

-0.66

>>>>>>>>

-0.65

POSITIVE LOGITS

 havoc

1.15

ous

0.90

ously

0.86

OUS

0.81

 spoil

0.79

spo

0.78

 ruined

0.76

ifully

0.76

 ruining

0.75

 ruin

0.74

Activations Density 0.039%

warnings or negative implications related to actions that can lead to significant negative consequences

instances of the word "ruin" and its variations indicating negative consequences

No Comments

No Known Activations