INDEX

Explanations

phrases indicating actions that are performed or not performed

oai_token-act-pair · gpt-3.5-turbo

instances of the word "did."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Methods

-0.71

liner

-0.70

Tier

-0.70

Tai

-0.69

washer

-0.68

case

-0.67

oided

-0.67

 Handling

-0.66

stood

-0.66

bent

-0.66

POSITIVE LOGITS

actic

0.99

pez

0.88

ĸļ

0.84

not

0.82

 confir

0.81

 indeed

0.77

oms

0.75

anos

0.74

ppel

0.74

 manage

0.74

Activations Density 0.079%

phrases indicating actions that are performed or not performed

instances of the word "did."

No Comments

No Known Activations