INDEX

Explanations

comparisons using the word "as" to highlight similarities or equivalents

oai_token-act-pair · gpt-3.5-turbo

comparisons using the word "as."

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

eri

-0.75

nce

-0.68

reated

-0.66

NL

-0.66

leneck

-0.64

Cause

-0.63

Sensor

-0.63

YD

-0.62

ainer

-0.62

heast

-0.62

POSITIVE LOGITS

 possible

0.77

lihood

0.74

pects

0.73

 practicable

0.72

gypt

0.70

 ours

0.69

ernels

0.67

 peas

0.67

par

0.65

packages

0.65

Activations Density 0.062%

comparisons using the word "as" to highlight similarities or equivalents

comparisons using the word "as."

No Comments

No Known Activations