INDEX

Explanations

phrases related to a decrease or decline in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to decreasing trends or drops in various metrics or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

archives

-0.73

 Founding

-0.67

ĳå£«

-0.63

sit

-0.63

ãĤ¨ãĥ«

-0.63

Ô

-0.62

swick

-0.62

tein

-0.62

ZI

-0.61

 Paste

-0.59

POSITIVE LOGITS

 drastically

1.30

 dramatically

1.27

 sharply

1.25

 markedly

1.15

 precip

1.13

 considerably

1.13

 exponentially

1.11

 substantially

1.09

 significantly

1.05

 accordingly

1.02

Activations Density 0.170%

phrases related to a decrease or decline in various contexts

references to decreasing trends or drops in various metrics or conditions

No Comments

No Known Activations