INDEX

Explanations

dates and specific events listed in a sequential order

oai_token-act-pair · gpt-3.5-turbo

references to sports events, specifically losses and victories in matches

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

DOD

-0.71

 FOIA

-0.68

FBI

-0.65

resist

-0.64

ATF

-0.62

 Garfield

-0.62

dy

-0.61

FBI

-0.60

 nonviolent

-0.59

 Yellowstone

-0.59

POSITIVE LOGITS

 qualifiers

0.85

 unbeaten

0.85

 whilst

0.84

 qualifier

0.83

 onwards

0.79

 qualification

0.76

 Fifa

0.75

 Belfast

0.75

 opener

0.74

 Klopp

0.74

Activations Density 0.406%

dates and specific events listed in a sequential order

references to sports events, specifically losses and victories in matches

No Comments

No Known Activations