INDEX

Explanations

words related to the abbreviation "AM"

oai_token-act-pair · gpt-3.5-turbo

references to the term "AM" in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ttes

-0.92

hered

-0.66

essee

-0.65

vous

-0.64

 hazard

-0.62

 puberty

-0.61

 Durham

-0.61

zzi

-0.60

cko

-0.60

 proc

-0.59

POSITIVE LOGITS

AZ

1.41

OUNT

1.21

NH

1.17

endment

1.10

ARC

1.06

HER

1.04

sterdam

1.02

BER

1.02

ILY

1.02

OUN

0.98

Activations Density 0.025%

words related to the abbreviation "AM"

references to the term "AM" in various contexts

No Comments

No Known Activations