INDEX

Explanations

terms or phrases indicating a transition or shift in focus

oai_token-act-pair · gpt-3.5-turbo

references to collective experiences and interactions

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

Negative Logits

 extent

-0.64

¶ħ

-0.63

²¾

-0.58

¿½

-0.58

Ĵ

-0.56

rika

-0.55

Ĭ±

-0.55

 minced

-0.54

MN

-0.54

 Coalition

-0.53

POSITIVE LOGITS

 away

0.95

 closer

0.93

 into

0.91

 onwards

0.89

into

0.89

 forth

0.85

 nearer

0.84

 ashore

0.83

 down

0.80

 Into

0.80

Activations Density 0.095%

terms or phrases indicating a transition or shift in focus

references to collective experiences and interactions

No Known Activations