INDEX

Explanations

relevant mentions of the abbreviation "DA" within a text

oai_token-act-pair · gpt-3.5-turbo

references to a specific organization or authority

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

naires

-0.77

packing

-0.73

kies

-0.72

sets

-0.71

falls

-0.71

achu

-0.70

ments

-0.69

ties

-0.68

 Dragonbound

-0.67

erous

-0.66

POSITIVE LOGITS

ILY

1.27

VID

1.12

BLE

0.99

WN

0.99

VIS

0.96

ZZ

0.92

OTA

0.92

VE

0.90

hyde

0.84

ZE

0.84

Activations Density 0.011%

relevant mentions of the abbreviation "DA" within a text

references to a specific organization or authority

No Comments

No Known Activations