INDEX

Explanations

phrases related to taking action or making decisions based on specific information or events

oai_token-act-pair · gpt-3.5-turbo

phrases related to taking action or making decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 ceilings

-0.72

gem

-0.70

 jars

-0.66

Tokens

-0.65

brew

-0.65

aways

-0.65

 chromosomes

-0.64

comings

-0.63

 Printed

-0.62

ighting

-0.61

POSITIVE LOGITS

 opposite

0.74

 ACTIONS

0.72

 behalf

0.71

fid

0.69

 differently

0.68

RECT

0.67

ĪĴ

0.67

ãĥĨ

0.66

uously

0.66

duty

0.66

Activations Density 0.129%

phrases related to taking action or making decisions based on specific information or events

phrases related to taking action or making decisions

No Comments

No Known Activations