INDEX

Explanations

numbers related to specific events or topics

oai_token-act-pair · gpt-3.5-turbo

numerical figures and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 millenn

-0.90

 nomine

-0.79

anooga

-0.69

 tradem

-0.68

ouver

-0.66

icial

-0.66

lings

-0.65

 lapt

-0.65

ŃĶ

-0.65

 glim

-0.65

POSITIVE LOGITS

 partName

1.17

/?

1.00

/#

0.99

0.97

0.96

0.95

Activations Density 0.044%

numbers related to specific events or topics

numerical figures and statistics

No Comments

No Known Activations