INDEX

Explanations

technical terms related to programming, pointers, and code implementation

oai_token-act-pair · gpt-3.5-turbo

terms related to coding and programming concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

earchers

-0.77

-0.73

alon

-0.70

ander

-0.70

awed

-0.69

tested

-0.69

 seiz

-0.68

proven

-0.66

aden

-0.66

afety

-0.65

POSITIVE LOGITS

ness

1.01

ity

0.93

 ones

0.89

ities

0.83

ly

0.81

 mode

0.79

 minded

0.79

NESS

0.78

 nature

0.70

 Ones

0.65

Activations Density 0.261%

technical terms related to programming, pointers, and code implementation

terms related to coding and programming concepts

No Comments

No Known Activations