INDEX

Explanations

words related to various types of elections or sports

oai_token-act-pair · gpt-3.5-turbo

references to sports, health, and elections

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

 ç¥ŀ

-0.76

 vain

-0.73

ixtape

-0.69

onies

-0.69

apes

-0.69

ifles

-0.68

 flatt

-0.68

 detachment

-0.66

ictions

-0.64

olson

-0.64

POSITIVE LOGITS

 Matters

0.97

 Affairs

0.96

Day

0.95

Aid

0.92

 Week

0.92

 Services

0.90

 Lobby

0.87

 Accountability

0.86

 Authority

0.85

Net

0.84

Activations Density 0.523%

words related to various types of elections or sports

references to sports, health, and elections

No Comments

No Known Activations