INDEX

Explanations

words related to gravity or emphasis

oai_token-act-pair · gpt-3.5-turbo

terms related to gravity and its effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Continued

-0.74

ħĭ

-0.74

âķĲâķĲ

-0.69

DOS

-0.69

#$

-0.67

LEASE

-0.67

OOL

-0.64

eer

-0.64

66666666

-0.64

Assembly

-0.64

POSITIVE LOGITS

 grav

1.33

itating

1.22

itas

1.02

estones

0.98

itate

0.94

itates

0.93

itated

0.93

iton

0.86

iosity

0.85

bent

0.85

Activations Density 0.008%

words related to gravity or emphasis

terms related to gravity and its effects

No Comments

No Known Activations