INDEX

Explanations

phrases related to percentages and proportions

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate statistical accounting or representation

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

Lab

-0.76

soever

-0.72

conn

-0.72

notation

-0.70

forge

-0.70

urn

-0.69

je

-0.68

nex

-0.67

udos

-0.66

ikers

-0.65

POSITIVE LOGITS

 billions

0.73

vich

0.72

 centuries

0.70

 determining

0.70

tics

0.69

lain

0.67

Ĥª

0.66

 Flavoring

0.66

utical

0.65

bidden

0.64

Activations Density 0.055%

phrases related to percentages and proportions

phrases that indicate statistical accounting or representation

No Comments

No Known Activations