INDEX

Explanations

the word "Kas" in the text

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Kas" and its variations in the text

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

 Islanders

-0.84

ycle

-0.73

 poppy

-0.72

aneous

-0.71

UCT

-0.65

 cavity

-0.64

ACTED

-0.63

 mischief

-0.63

 combustion

-0.62

ODUCT

-0.60

POSITIVE LOGITS

imir

1.01

Kas

0.99

rils

0.98

assin

0.92

daq

0.91

ala

0.88

iewicz

0.87

bah

0.85

avin

0.84

sem

0.83

Activations Density 0.015%

the word "Kas" in the text

mentions of the name "Kas" and its variations in the text

No Comments

No Known Activations