INDEX

Explanations

phrases centered around a specific topic or entity

oai_token-act-pair · gpt-3.5-turbo

phrases that focus on the concept of being "centered around" or related to a specific topic

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

WI

-0.70

 tatt

-0.70

 Tigers

-0.68

ipl

-0.66

BT

-0.66

inen

-0.63

ippi

-0.62

owe

-0.60

opers

-0.60

hiba

-0.60

POSITIVE LOGITS

ãħĭ

0.79

loading

0.67

erous

0.66

rocal

0.65

 corners

0.64

 globalization

0.62

âĸ¬

0.62

Offline

0.61

 ..........

0.61

arde

0.60

Activations Density 0.040%

phrases centered around a specific topic or entity

phrases that focus on the concept of being "centered around" or related to a specific topic

No Comments

No Known Activations