INDEX

Explanations

terms related to extra-normal or very high amounts of a quality or concept

oai_token-act-pair · gpt-3.5-turbo

instances of the word "super" and its variations

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

 Seym

-0.74

edIn

-0.69

GGGG

-0.69

Reloaded

-0.69

theless

-0.67

 Frie

-0.67

 Lauder

-0.65

assetsadobe

-0.64

 Granger

-0.63

 Anger

-0.61

POSITIVE LOGITS

imposed

1.35

visor

1.24

visory

1.21

nova

1.17

charged

1.14

charg

1.13

cedes

1.12

posed

1.10

charging

1.06

position

1.06

Activations Density 0.019%

terms related to extra-normal or very high amounts of a quality or concept

instances of the word "super" and its variations

No Comments

No Known Activations