INDEX

Explanations

phrases related to making decisions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating decisions or actions taken by individuals or authorities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tips

-0.72

ILY

-0.72

models

-0.72

amon

-0.71

stories

-0.71

 Enemies

-0.71

Points

-0.71

NES

-0.69

fol

-0.68

Known

-0.67

POSITIVE LOGITS

 invoke

1.14

 seek

1.10

 pursue

1.10

 prioritize

1.05

 create

1.05

 revisit

1.05

 bring

1.05

 relocate

1.04

 revise

1.03

 declare

1.03

Activations Density 0.074%

phrases related to making decisions

phrases indicating decisions or actions taken by individuals or authorities

No Comments

No Known Activations