INDEX

Explanations

references to the model line "Mi" - possibly related to technology products or models

oai_token-act-pair · gpt-3.5-turbo

references to the Mi series of products

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

stall

-0.85

âķĲâķĲ

-0.80

fully

-0.78

nesday

-0.73

tions

-0.70

ful

-0.69

rition

-0.68

rooms

-0.67

*/(

-0.67

tons

-0.67

POSITIVE LOGITS

ata

0.93

ota

0.88

ovember

0.85

oche

0.84

omi

0.83

othal

0.82

ugi

0.81

obiles

0.80

oses

0.80

omed

0.78

Activations Density 0.018%

references to the model line "Mi" - possibly related to technology products or models

references to the Mi series of products

No Comments

No Known Activations