INDEX

Explanations

phrases related to specific organizations or programs with the abbreviation "NS"

oai_token-act-pair · gpt-3.5-turbo

terms related to a specific organization or system denoted by "NS"

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

standing

-0.73

icago

-0.70

oppers

-0.67

teen

-0.67

oise

-0.66

âĸ¬âĸ¬

-0.66

stown

-0.66

fare

-0.66

ously

-0.65

ths

-0.62

POSITIVE LOGITS

FW

1.27

HT

0.89

BM

0.84

ERC

0.83

IM

0.80

KB

0.80

CC

0.79

FG

0.78

ICS

0.77

AAF

0.76

Activations Density 0.019%

phrases related to specific organizations or programs with the abbreviation "NS"

terms related to a specific organization or system denoted by "NS"

No Comments

No Known Activations