INDEX

Explanations

keywords related to financial details or calculations

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate positive additions or increments

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

adr

-0.83

dfx

-0.81

stem

-0.81

abies

-0.80

bris

-0.79

rimp

-0.79

 Sparkle

-0.78

atters

-0.78

apers

-0.77

bare

-0.73

POSITIVE LOGITS

minus

0.76

/-

0.76

cules

0.76

 plus

0.75

 infinity

0.74

 append

0.71

 amen

0.71

++++

0.70

 assorted

0.69

-+-+-+-+

0.67

Activations Density 0.013%

keywords related to financial details or calculations

phrases that indicate positive additions or increments

No Comments

No Known Activations