INDEX

Explanations

mentions of technology products and models

oai_token-act-pair · gpt-3.5-turbo

references to the "One" brand or product name

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

="#

-0.72

lished

-0.71

ucl

-0.70

ruary

-0.66

ordes

-0.65

 actionGroup

-0.64

ulative

-0.63

aeda

-0.63

ãĥ¼

-0.62

apons

-0.62

POSITIVE LOGITS

 Hundred

1.04

 Thousand

0.84

 Million

0.82

 dimensional

0.80

 Direction

0.79

Drive

0.78

esan

0.77

 hundred

0.75

Shot

0.75

elf

0.75

Activations Density 0.085%

mentions of technology products and models

references to the "One" brand or product name

No Comments

No Known Activations