INDEX

Explanations

positive adjectives that denote approval or success

oai_token-act-pair · gpt-3.5-turbo

emotional responses and subjective evaluations of situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

OTUS

-0.67

 Allies

-0.66

 remission

-0.65

hari

-0.65

velt

-0.63

 sane

-0.63

((

-0.62

llah

-0.61

 coherent

-0.61

dayName

-0.61

POSITIVE LOGITS

 hindered

1.22

 lacked

1.16

 hampered

1.15

 drawbacks

1.15

 cautioned

1.08

 downside

1.06

 lacks

1.06

 struggled

1.04

 shortcomings

1.03

 disappoint

1.03

Activations Density 0.607%

positive adjectives that denote approval or success

emotional responses and subjective evaluations of situations

No Comments

No Known Activations