INDEX

Explanations

percentages and numerical values, specifically focusing on percentages, probabilities, and quantities

oai_token-act-pair · gpt-3.5-turbo

statistical data or numerical information regarding percentages and probabilities

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

wagen

-0.64

CVE

-0.63

 pseud

-0.62

Merit

-0.60

RAW

-0.60

Queue

-0.60

AFL

-0.57

Ļ½

-0.55

virt

-0.54

 Orient

-0.54

POSITIVE LOGITS

lycer

0.81

pees

0.80

ngth

0.77

ãĥĻ

0.75

amic

0.73

oway

0.71

chini

0.68

opy

0.65

ogether

0.65

assium

0.65

Activations Density 0.248%

percentages and numerical values, specifically focusing on percentages, probabilities, and quantities

statistical data or numerical information regarding percentages and probabilities

No Comments

No Known Activations