INDEX

Explanations

verbs related to decision-making and preferences

oai_token-act-pair · gpt-3.5-turbo

phrases related to preferences or tendencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

AIDS

-0.68

ankind

-0.66

 violates

-0.65

harm

-0.64

awaited

-0.63

soever

-0.62

Govern

-0.62

sylvania

-0.61

lihood

-0.61

itous

-0.61

POSITIVE LOGITS

 preferring

0.81

iet

0.77

 preferred

0.77

 caution

0.72

ãĤ©

0.72

foc

0.70

oof

0.70

 Preferred

0.70

 prefer

0.70

 prioritize

0.70

Activations Density 0.739%

verbs related to decision-making and preferences

phrases related to preferences or tendencies

No Comments

No Known Activations