INDEX

Explanations

words related to overflow or overcrowding

oai_token-act-pair · gpt-3.5-turbo

terms related to overflowing or overpopulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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¥³

-0.78

dar

-0.70

beard

-0.70

onna

-0.70

DAY

-0.69

apple

-0.68

 tooth

-0.67

 sweat

-0.64

ect

-0.64

otine

-0.63

POSITIVE LOGITS

 overfl

0.86

izoph

0.84

idth

0.82

capacity

0.78

imates

0.78

 overflow

0.75

aturated

0.73

aucus

0.72

ollen

0.70

assi

0.69

Activations Density 0.019%

words related to overflow or overcrowding

terms related to overflowing or overpopulation

No Comments

No Known Activations