INDEX

Explanations

examples and explanations in a context

oai_token-act-pair · gpt-3.5-turbo

phrases that introduce examples or explanations

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

roy

-0.78

ess

-0.70

gaard

-0.69

owed

-0.69

esses

-0.68

inate

-0.65

ige

-0.64

GM

-0.63

 inev

-0.63

ND

-0.61

POSITIVE LOGITS

ierre

0.77

zech

0.69

hov

0.68

tti

0.68

trak

0.67

gans

0.66

 Photographer

0.64

=#

0.64

ooters

0.63

 Reflex

0.63

Activations Density 0.104%

examples and explanations in a context

phrases that introduce examples or explanations

No Comments

No Known Activations