INDEX

Explanations

instances of the word "Me"

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Me."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

pole

-0.77

 totality

-0.70

 slic

-0.67

 corners

-0.65

paralle

-0.64

 legality

-0.64

ordinate

-0.63

medium

-0.61

 validity

-0.61

Closure

-0.60

POSITIVE LOGITS

asuring

1.31

asured

1.20

zzo

1.20

cca

1.16

asure

1.15

adow

1.13

aning

1.12

asures

1.10

lda

1.07

eker

1.07

Activations Density 0.026%

instances of the word "Me"

mentions of the word "Me."

No Comments

No Known Activations