INDEX

Explanations

sentences related to comparisons or findings using analytical or scientific language

oai_token-act-pair · gpt-3.5-turbo

terms related to scientific analysis or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 ðŁ

-0.64

Buzz

-0.63

Thumbnail

-0.62

 dystop

-0.62

 inspires

-0.61

yt

-0.61

omics

-0.59

AFP

-0.59

 explores

-0.58

é»Ĵ

-0.58

POSITIVE LOGITS

 residual

0.61

 maintenance

0.59

 defective

0.58

 supra

0.57

 Maintenance

0.57

CLR

0.56

HW

0.56

 improper

0.56

 facult

0.56

 supplementary

0.55

Activations Density 1.518%

sentences related to comparisons or findings using analytical or scientific language

terms related to scientific analysis or evaluations

No Comments

No Known Activations