INDEX

Explanations

mentions of the acronym "ML" with various numerical identifiers

oai_token-act-pair · gpt-3.5-turbo

references to Major League Baseball (MLB)

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Gamble

-0.77

nces

-0.74

-0.72

 Wildcats

-0.70

ãĥĦ

-0.67

esville

-0.66

ãĥĹ

-0.66

ãĥ¼ãĥ«

-0.66

fulness

-0.64

panic

-0.63

POSITIVE LOGITS

ML

1.10

TON

0.87

anguage

0.86

NF

0.84

endon

0.83

MT

0.82

arge

0.78

NP

0.78

DN

0.76

osition

0.76

Activations Density 0.006%

mentions of the acronym "ML" with various numerical identifiers

references to Major League Baseball (MLB)

No Comments

No Known Activations