INDEX

Explanations

mentions of the term "multiple"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "multiple" 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 @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Dialogue

-0.75

ESE

-0.74

iquette

-0.71

nothing

-0.70

NER

-0.70

ney

-0.68

OST

-0.68

brance

-0.67

NEY

-0.67

ONEY

-0.65

POSITIVE LOGITS

 sclerosis

1.64

xes

1.49

 iterations

1.17

 layers

1.08

ples

1.07

 instances

1.03

 facets

1.02

 generations

1.01

 avenues

1.01

 versions

1.00

Activations Density 0.033%

mentions of the term "multiple"

occurrences of the word "multiple" in various contexts

No Comments

No Known Activations