INDEX

Explanations

phrases related to personal experiences or emotions

oai_token-act-pair · gpt-3.5-turbo

phrases that explore the concept of experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

oak

-0.67

dash

-0.65

NetMessage

-0.62

 Inher

-0.62

eous

-0.61

riad

-0.61

Continue

-0.61

Kings

-0.61

camp

-0.60

 Galile

-0.59

POSITIVE LOGITS

 entails

1.15

 means

1.12

 meant

1.04

 takes

0.99

 entail

0.98

 Means

0.98

 mean

0.97

 feels

0.96

 boils

0.88

 signifies

0.86

Activations Density 0.043%

phrases related to personal experiences or emotions

phrases that explore the concept of experience

No Comments

No Known Activations