INDEX

Explanations

words related to actions, behaviors, and activities

oai_token-act-pair · gpt-3.5-turbo

action words related to various activities and behaviors

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

Not in Any Lists

No Comments

Negative Logits

berus

-0.74

Applic

-0.74

éĹ

-0.66

affer

-0.66

ãĥķãĤ©

-0.66

imbabwe

-0.63

fired

-0.62

FK

-0.62

zero

-0.61

sama

-0.61

POSITIVE LOGITS

 themselves

0.97

 theirs

0.93

 their

0.90

 alike

0.81

 THEIR

0.80

 differently

0.79

 freely

0.65

their

0.64

 yearly

0.62

 instinctively

0.62

Activations Density 0.469%

words related to actions, behaviors, and activities

action words related to various activities and behaviors

No Comments

No Known Activations