INDEX

Explanations

phrases indicating actions or interactions among individuals

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "we" and the related themes of togetherness and shared experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Downloadha

-0.70

ocity

-0.66

ocl

-0.65

alys

-0.63

Pwr

-0.63

grave

-0.62

fect

-0.62

matter

-0.62

forms

-0.61

rising

-0.61

POSITIVE LOGITS

 parted

1.03

IRD

0.85

 helicop

0.85

 mutually

0.84

emate

0.84

 adjourn

0.83

 together

0.83

 brainstorm

0.83

Chat

0.82

 Together

0.80

Activations Density 0.274%

phrases indicating actions or interactions among individuals

occurrences of the word "we" and the related themes of togetherness and shared experiences

No Comments

No Known Activations