INDEX

Explanations

mentions or references to manufacturers or products created by manufacturers

oai_token-act-pair · gpt-3.5-turbo

references to manufacturers and their products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

mire

-0.83

rina

-0.75

visor

-0.69

mins

-0.64

 Warden

-0.64

ormal

-0.62

retion

-0.62

 sher

-0.61

 Bagg

-0.61

ctica

-0.59

POSITIVE LOGITS

 manufactures

0.87

ãĤ®

0.82

 warranties

0.81

paces

0.78

 manufacturers

0.78

 Electronics

0.78

ãĤ´

0.75

 Warranty

0.73

 Manufact

0.72

è»

0.72

Activations Density 0.082%

mentions or references to manufacturers or products created by manufacturers

references to manufacturers and their products

No Comments

No Known Activations