INDEX

Explanations

phrases that start with "Simply" and provide a straightforward statement or explanation

oai_token-act-pair · gpt-3.5-turbo

the word "simply" and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

afort

-0.71

 seriously

-0.69

mostly

-0.64

asta

-0.63

 definitely

-0.63

 actually

-0.62

luster

-0.62

 Mostly

-0.62

 PLUS

-0.61

emis

-0.60

POSITIVE LOGITS

ifiable

0.78

 shrugged

0.74

 cannot

0.69

 stated

0.69

 incapable

0.68

tons

0.67

 ignored

0.65

 redistributed

0.65

cos

0.65

kt

0.64

Activations Density 0.051%

phrases that start with "Simply" and provide a straightforward statement or explanation

the word "simply" and its variations in context

No Comments

No Known Activations