INDEX

Explanations

phrases related to identification and quantification

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "identify" and its variants along with quantifying concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 turkey

-0.65

awa

-0.65

ħĭ

-0.64

 cutter

-0.63

 miscarriage

-0.62

 puff

-0.62

 Spice

-0.62

Ħ¢

-0.61

 jerk

-0.61

 pump

-0.60

POSITIVE LOGITS

ified

2.37

ifying

2.35

ification

2.21

ifies

2.14

ifiers

2.13

ifier

2.11

ifications

1.97

ifiable

1.91

ify

1.91

ities

1.81

Activations Density 0.084%

phrases related to identification and quantification

occurrences of the term "identify" and its variants along with quantifying concepts

No Comments

No Known Activations