INDEX

Explanations

propositions indicating location or direction

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to influential topics or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 typical

-0.67

 elaborate

-0.67

 exact

-0.66

 unusually

-0.63

 repeated

-0.61

 soothing

-0.61

 scattered

-0.60

 prolonged

-0.60

 resorted

-0.60

 ..........

-0.60

POSITIVE LOGITS

Ħ¢

0.84

ciation

0.84

 Americas

0.84

culosis

0.80

swer

0.80

life

0.79

ocracy

0.78

laws

0.77

omics

0.76

Trade

0.76

Activations Density 0.480%

propositions indicating location or direction

words and phrases related to influential topics or entities

No Comments

No Known Activations