INDEX

Explanations

times or intervals mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

key phrases and statistics related to comparisons and relationships between entities

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

cipled

-0.62

ulty

-0.58

collect

-0.58

ificant

-0.57

oyal

-0.56

eous

-0.55

asonable

-0.55

ivers

-0.54

 behaviors

-0.53

posted

-0.53

POSITIVE LOGITS

 Quake

0.65

 Belg

0.62

 Earthqu

0.61

kson

0.60

Bav

0.60

ogun

0.59

 Bast

0.58

Bin

0.55

 Boko

0.54

coni

0.54

Activations Density 1.155%

times or intervals mentioned in the text

key phrases and statistics related to comparisons and relationships between entities

No Comments

No Known Activations