INDEX

Explanations

phrases or words related to recent or newly introduced things

oai_token-act-pair · gpt-3.5-turbo

instances of the word "newly."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĺħ

-0.83

 Citation

-0.82

essee

-0.70

 willpower

-0.67

 Trace

-0.66

 Attribution

-0.63

 Waste

-0.62

 Coverage

-0.61

raints

-0.60

 Grail

-0.60

POSITIVE LOGITS

mint

1.25

wed

1.22

 mint

1.17

 appointed

1.16

released

1.06

 crowned

1.04

 hatched

1.03

 released

1.02

 formed

1.00

 renovated

1.00

Activations Density 0.019%

phrases or words related to recent or newly introduced things

instances of the word "newly."

No Comments

No Known Activations