INDEX

Explanations

phrases related to the number "two"

oai_token-act-pair · gpt-3.5-turbo

the repetition of the word "two."

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

ugu

-0.82

asta

-0.76

amaru

-0.72

 Caption

-0.69

lus

-0.68

ashtra

-0.68

rir

-0.67

ICLE

-0.65

ULE

-0.63

needs

-0.63

POSITIVE LOGITS

 thirds

1.60

 dozen

1.13

 hundred

1.06

 weeks

1.04

 halves

1.02

fold

0.99

teenth

0.95

 decades

0.88

teen

0.88

een

0.88

Activations Density 0.129%

phrases related to the number "two"

the repetition of the word "two."

No Comments

No Known Activations