INDEX

Explanations

phrases related to the action of "handing" something to someone

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "handed."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

00200000

-0.70

 Tonight

-0.68

issy

-0.67

natureconservancy

-0.65

amins

-0.64

urity

-0.64

ITAL

-0.64

alli

-0.62

POSITIVE LOGITS

shake

0.90

 handed

0.86

awed

0.84

handed

0.80

maid

0.76

washing

0.75

ily

0.74

 wielded

0.73

wheel

0.72

ragon

0.72

Activations Density 0.011%

phrases related to the action of "handing" something to someone

occurrences of the word "handed."

No Comments

No Known Activations