INDEX

Explanations

references to historical time periods

oai_token-act-pair · gpt-3.5-turbo

references to specific centuries in historical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

aturday

-0.93

ECTION

-0.81

hod

-0.80

imon

-0.78

TPPStreamerBot

-0.78

iquid

-0.75

uala

-0.75

MAT

-0.73

clips

-0.72

ciating

-0.71

POSITIVE LOGITS

BCE

0.93

 onwards

0.91

 onward

0.80

 Anglo

0.72

 British

0.71

 Victorian

0.71

 colonial

0.71

AD

0.70

CE

0.70

 Revival

0.70

Activations Density 0.050%

references to historical time periods

references to specific centuries in historical contexts

No Comments

No Known Activations