INDEX

Explanations

words related to programming headers or configurations

oai_token-act-pair · gpt-3.5-turbo

mentions of header files in programming contexts

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

VK

-0.72

uating

-0.69

ingo

-0.66

atile

-0.66

quit

-0.65

å¥³

-0.64

negie

-0.64

arak

-0.64

ç¥ŀ

-0.63

itan

-0.63

POSITIVE LOGITS

dress

0.91

 headers

0.89

 header

0.83

anded

0.81

quartered

0.79

 drawer

0.76

header

0.72

otle

0.71

plate

0.70

headers

0.69

Activations Density 0.018%

words related to programming headers or configurations

mentions of header files in programming contexts

No Comments

No Known Activations