INDEX

Explanations

instructions for performing actions or tasks

oai_token-act-pair · gpt-3.5-turbo

references to the reader's actions and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ooters

-0.63

aughs

-0.63

 abound

-0.62

recy

-0.62

acular

-0.62

 perks

-0.61

 unthinkable

-0.61

WAYS

-0.61

 reperto

-0.60

eties

-0.59

POSITIVE LOGITS

 intended

0.93

 selected

0.91

umbn

0.91

 originally

0.89

 chosen

0.86

 requested

0.84

 assigned

0.82

 desired

0.80

 supposed

0.78

 photographed

0.76

Activations Density 0.221%

instructions for performing actions or tasks

references to the reader's actions and experiences

No Comments

No Known Activations