INDEX

Explanations

words related to awakening or becoming active

oai_token-act-pair · gpt-3.5-turbo

instances of the word "aw"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Prelude

-0.69

 prelim

-0.69

MSM

-0.69

 prol

-0.68

 counters

-0.62

 methyl

-0.60

 Latino

-0.60

 singles

-0.59

 Strat

-0.59

STR

-0.59

POSITIVE LOGITS

aw

4.32

aws

2.68

awed

2.67

awatts

1.90

AW

1.88

awa

1.59

awk

1.49

awar

1.45

awan

1.42

awi

1.41

Activations Density 0.016%

words related to awakening or becoming active

instances of the word "aw"

No Comments

No Known Activations