INDEX

Explanations

demonstrations of quantities, such as dimensions or measurements, with a focus on significant amounts

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate quantities or measurements

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

aci

-0.73

alog

-0.70

itivity

-0.67

ç«

-0.66

hill

-0.66

 guiActiveUn

-0.65

anos

-0.65

iets

-0.65

onent

-0.64

alogy

-0.64

POSITIVE LOGITS

 possible

1.16

 practicable

0.94

 imaginable

0.83

 conceivable

0.81

0.80

0.79

 THREE

0.78

 Possible

0.77

Activations Density 0.034%

demonstrations of quantities, such as dimensions or measurements, with a focus on significant amounts

phrases that indicate quantities or measurements

No Comments

No Known Activations