INDEX

Explanations

occurrences where something goes wrong or there is a negative outcome

oai_token-act-pair · gpt-3.5-turbo

phrases that repeatedly use the word "only."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

insula

-0.74

ahime

-0.74

idon

-0.70

lass

-0.68

align

-0.66

multipl

-0.66

hement

-0.65

ducers

-0.64

PK

-0.63

arthy

-0.61

POSITIVE LOGITS

 marginally

0.99

 kidding

0.94

 incidentally

0.84

 spor

0.81

 seconds

0.80

 minutes

0.79

 surpassed

0.75

 vaguely

0.74

 days

0.72

 briefly

0.72

Activations Density 0.066%

occurrences where something goes wrong or there is a negative outcome

phrases that repeatedly use the word "only."

No Comments

No Known Activations