INDEX

Explanations

references to historical figures or specific names, especially related to Jefferson

oai_token-act-pair · gpt-3.5-turbo

references to Thomas Jefferson

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

-0.83

lator

-0.74

uling

-0.70

other

-0.68

comed

-0.66

arer

-0.66

eq

-0.66

atics

-0.65

spring

-0.65

fare

-0.65

POSITIVE LOGITS

 Jefferson

1.12

 Parish

1.06

 Davis

0.91

sburg

0.89

agne

0.85

shire

0.80

 Adams

0.79

 County

0.78

 Mills

0.78

izabeth

0.74

Activations Density 0.018%

references to historical figures or specific names, especially related to Jefferson

references to Thomas Jefferson

No Comments

No Known Activations