INDEX

Explanations

Nvidia GeForce graphics cards models

oai_token-act-pair · gpt-3.5-turbo

specific graphics card models and their performance metrics

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

juries

-0.70

staking

-0.70

pmwiki

-0.69

taining

-0.68

ocre

-0.67

âĹ¼

-0.67

ocrates

-0.66

bsite

-0.66

intendent

-0.66

etime

-0.66

POSITIVE LOGITS

GAM

0.76

 Gaming

0.76

 chipset

0.75

Ti

0.71

 GPUs

0.70

USB

0.69

XT

0.69

 Accessories

0.69

DAC

0.67

 chassis

0.67

Activations Density 0.047%

Nvidia GeForce graphics cards models

specific graphics card models and their performance metrics

No Comments

No Known Activations