INDEX

Explanations

phrases related to locations or businesses containing the word "hop"

oai_token-act-pair · gpt-3.5-turbo

words related to "hop" or "hopping."

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

 bruising

-0.81

Downloadha

-0.67

 Frankenstein

-0.67

 behold

-0.65

 Dynamics

-0.65

 Monstrous

-0.64

UCT

-0.63

ãĥīãĥ©ãĤ´ãĥ³

-0.63

APS

-0.62

 wolves

-0.62

POSITIVE LOGITS

efully

1.56

eful

1.47

eless

1.21

hop

1.02

emaker

0.98

daq

0.98

Hop

0.98

inion

0.92

yright

0.92

lins

0.89

Activations Density 0.026%

phrases related to locations or businesses containing the word "hop"

words related to "hop" or "hopping."

No Comments

No Known Activations