INDEX

Explanations

phrases related to adopting policies, technologies, values, or behaviors

oai_token-act-pair · gpt-3.5-turbo

instances of the word "adopt" and its variations

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

 Frie

-0.77

wall

-0.70

jandro

-0.62

 Randall

-0.62

MSG

-0.61

 Volcano

-0.60

LIM

-0.60

ulla

-0.59

 Puzzle

-0.59

Yah

-0.58

POSITIVE LOGITS

 adopt

3.62

 adoption

2.42

 adop

2.41

 adopting

2.35

 adopted

2.11

 adoptive

1.58

 embrace

1.36

 foster

1.35

 abandon

1.24

 promul

1.22

Activations Density 0.011%

phrases related to adopting policies, technologies, values, or behaviors

instances of the word "adopt" and its variations

No Comments

No Known Activations