INDEX

Explanations

words related to reputation or status

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to reputation and related concepts

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

href

-0.65

 Watson

-0.64

ouri

-0.64

Land

-0.64

âĹı

-0.63

 Schultz

-0.62

PNG

-0.62

Wall

-0.61

Bee

-0.61

 SNAP

-0.60

POSITIVE LOGITS

rupulous

0.77

ãĤ´ãĥ³

0.76

=#

0.76

ursed

0.75

tsky

0.75

alez

0.71

arr

0.70

ignty

0.70

 coats

0.68

osate

0.67

Activations Density 0.141%

words related to reputation or status

words and phrases related to reputation and related concepts

No Comments

No Known Activations