INDEX

Explanations

words related to curses

oai_token-act-pair · gpt-3.5-turbo

words related to curses and their effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Resp

-0.77

TAG

-0.76

inton

-0.75

 Intercept

-0.73

ocal

-0.71

 Stephenson

-0.70

 Stephan

-0.69

 Marin

-0.69

rooms

-0.68

immers

-0.68

POSITIVE LOGITS

 curse

3.78

 curses

2.99

 Curse

2.81

 cursed

2.68

 cursing

2.25

ursed

1.89

 Cursed

1.74

urse

1.72

urses

1.46

 plague

1.44

Activations Density 0.034%

words related to curses

words related to curses and their effects

No Comments

No Known Activations