INDEX

Explanations

phrases related to unspecified quantities or unspecified entities

oai_token-act-pair · gpt-3.5-turbo

the word "some" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

SPONSORED

-0.82

enance

-0.77

ades

-0.67

raid

-0.67

meet

-0.66

ettes

-0.63

alties

-0.63

Reviewer

-0.63

ade

-0.62

agents

-0.61

POSITIVE LOGITS

place

0.97

how

0.93

ones

0.85

body

0.81

 semblance

0.80

 degree

0.78

 consolation

0.74

HOW

0.69

 additional

0.68

 considerable

0.63

Activations Density 0.088%

phrases related to unspecified quantities or unspecified entities

the word "some" in various contexts

No Comments

No Known Activations