INDEX

Explanations

technical terms and processes related to equipment and operations

oai_token-act-pair · gpt-3.5-turbo

terms related to measurement and evaluation 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 @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å§«

-0.75

thumbnails

-0.75

ãģĦ

-0.75

ãĥ´

-0.75

ãĥĬ

-0.74

ãĥ©ãĥ³

-0.71

ç¥ŀ

-0.69

ãģ£

-0.67

STATE

-0.66

æ©

-0.65

POSITIVE LOGITS

for

0.76

undown

0.74

reements

0.69

alions

0.64

 underway

0.63

 extraord

0.62

backs

0.61

 Bezos

0.61

ousel

0.60

ilitating

0.59

Activations Density 0.627%

technical terms and processes related to equipment and operations

terms related to measurement and evaluation in various contexts

No Comments

No Known Activations