INDEX

Explanations

comparisons or quantities pertaining to a higher number of something

oai_token-act-pair · gpt-3.5-turbo

quantitative expressions indicating larger quantities

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

ĺħ

-0.82

xtap

-0.80

ode

-0.74

DER

-0.70

ÃŁ

-0.69

Fram

-0.68

imaru

-0.67

oes

-0.66

Gra

-0.66

[|

-0.65

POSITIVE LOGITS

 than

1.25

 stringent

1.08

 sophisticated

0.97

ado

0.87

 diverse

0.86

 extensive

0.86

 elaborate

0.85

 detailed

0.85

 rigorous

0.84

 frequent

0.83

Activations Density 0.149%

comparisons or quantities pertaining to a higher number of something

quantitative expressions indicating larger quantities

No Comments

No Known Activations