INDEX

Explanations

phrases related to problem-solving or resolution

oai_token-act-pair · gpt-3.5-turbo

instances of the word "resolved" and its variations, indicating the resolution of issues or situations

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

inges

-0.85

aneers

-0.78

ista

-0.77

istas

-0.76

anto

-0.74

wx

-0.74

eries

-0.73

eners

-0.73

uts

-0.72

eway

-0.68

POSITIVE LOGITS

 solved

0.98

ĸļ

0.95

 resolved

0.83

CLASSIFIED

0.78

actionDate

0.73

olved

0.71

lucent

0.71

0.70

 unanimously

0.70

thumbnails

0.69

Activations Density 0.016%

phrases related to problem-solving or resolution

instances of the word "resolved" and its variations, indicating the resolution of issues or situations

No Comments

No Known Activations