INDEX

Explanations

sports-related activities such as making saves, scoring points, and shooting goals

oai_token-act-pair · gpt-3.5-turbo

occurrences of punctuation and numerical indicators in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ń·

-0.91

swer

-0.76

istani

-0.72

ensibly

-0.69

 legally

-0.68

 popul

-0.67

ataka

-0.66

onym

-0.66

 answ

-0.66

 ç¥ŀ

-0.66

POSITIVE LOGITS

Fresh

0.89

Outside

0.87

Late

0.87

Heat

0.85

Ble

0.84

Kenn

0.83

WHAT

0.83

Land

0.82

Players

0.82

Tra

0.82

Activations Density 0.210%

sports-related activities such as making saves, scoring points, and shooting goals

occurrences of punctuation and numerical indicators in the text

No Comments

No Known Activations