INDEX

Explanations

terms related to the brand or entity "Agora"

oai_token-act-pair · gpt-3.5-turbo

the presence of the word "Ag" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Dare

-0.82

 Jenner

-0.77

 sight

-0.71

 Cors

-0.68

ãĥīãĥ©ãĤ´ãĥ³

-0.68

ĸļ

-0.68

 directions

-0.67

OCK

-0.65

 Tycoon

-0.65

side

-0.62

POSITIVE LOGITS

reement

1.38

reements

1.25

raham

1.14

nostic

1.05

reed

1.04

raf

1.03

ora

1.01

ree

0.99

atha

0.97

mination

0.96

Activations Density 0.024%

terms related to the brand or entity "Agora"

the presence of the word "Ag" in various contexts

No Comments

No Known Activations