INDEX

Explanations

phrases indicating adoption, popularity, or acceptance

oai_token-act-pair · gpt-3.5-turbo

phrases indicating activation or engagement with something

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

Ĥª

-0.72

 msec

-0.61

Ķ

-0.60

BUT

-0.60

aurus

-0.59

-0.58

©¶æ¥µ

-0.57

Ĥİ

-0.54

cpp

-0.54

¿½

-0.53

POSITIVE LOGITS

 behalf

1.29

erous

1.07

shore

1.07

etime

0.97

screen

0.91

top

0.86

eday

0.83

 board

0.82

yx

0.80

demand

0.80

Activations Density 0.083%

phrases indicating adoption, popularity, or acceptance

phrases indicating activation or engagement with something

No Comments

No Known Activations