INDEX

Explanations

phrases related to progress or advancement

oai_token-act-pair · gpt-3.5-turbo

instances of the word "up" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Â¯Â¯Â¯Â¯

-0.65

 CLSID

-0.62

VICE

-0.62

TY

-0.62

 Munich

-0.61

________________________

-0.61

 understatement

-0.60

Maker

-0.60

 Canaveral

-0.58

POSITIVE LOGITS

grading

1.33

grades

1.26

graded

1.24

stairs

1.21

dates

1.19

dating

1.14

bringing

1.00

raised

0.97

swing

0.94

rights

0.94

Activations Density 0.059%

phrases related to progress or advancement

instances of the word "up" in various contexts

No Comments

No Known Activations