INDEX

Explanations

specific names or entities

oai_token-act-pair · gpt-3.5-turbo

the phrase "the likes of" used in various contexts, often referring to notable people or entities

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

arding

-0.79

INA

-0.75

 Ethics

-0.73

BILITIES

-0.66

INTON

-0.64

å£«

-0.63

ento

-0.62

verning

-0.61

 Springs

-0.61

angan

-0.61

POSITIVE LOGITS

liest

1.24

lihood

1.22

lier

1.10

liness

0.87

ettings

0.80

bill

0.73

creen

0.73

mith

0.71

hots

0.71

hai

0.68

Activations Density 0.016%

specific names or entities

the phrase "the likes of" used in various contexts, often referring to notable people or entities

No Comments

No Known Activations