INDEX

Explanations

phrases indicating intention or purpose

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "mind" and the concept of consideration

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

heres

-0.68

iott

-0.66

nect

-0.64

 recess

-0.63

hell

-0.60

Reviewed

-0.59

oqu

-0.59

phia

-0.58

mouth

-0.58

advert

-0.58

POSITIVE LOGITS

 when

0.85

 WHEN

0.71

oldown

0.64

rals

0.63

 dstg

0.63

enance

0.63

 whenever

0.61

aepernick

0.60

 budgetary

0.58

perature

0.58

Activations Density 0.090%

phrases indicating intention or purpose

mentions of the word "mind" and the concept of consideration

No Comments

No Known Activations