INDEX

Explanations

proper names related to the term "Ker"

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the name "Ker."

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

ãģį

-0.83

UME

-0.82

BOOK

-0.74

 à¨

-0.72

ÙĲ

-0.69

ãĥ¼ãĥ³

-0.69

IBLE

-0.67

naires

-0.67

UCT

-0.67

EMENT

-0.66

POSITIVE LOGITS

rigan

1.09

mit

1.06

der

1.01

sten

1.00

lein

0.97

bal

0.94

lins

0.92

bil

0.92

ston

0.92

lov

0.90

Activations Density 0.010%

proper names related to the term "Ker"

repeated mentions of the name "Ker."

No Comments

No Known Activations