INDEX

Explanations

phrases related to making errors or poor decisions

oai_token-act-pair · gpt-3.5-turbo

various types of decisions and mistakes in actions

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

iolet

-0.64

adow

-0.64

 Topics

-0.63

licks

-0.61

arling

-0.59

awed

-0.58

ongo

-0.58

aples

-0.57

ater

-0.57

redited

-0.56

POSITIVE LOGITS

 anew

0.79

liest

0.73

:]

0.70

olicy

0.69

Reloaded

0.64

 wisely

0.61

 bluntly

0.61

 sarcast

0.61

same

0.60

ultimate

0.60

Activations Density 0.214%

phrases related to making errors or poor decisions

various types of decisions and mistakes in actions

No Comments

No Known Activations