INDEX

Explanations

proper nouns related to a specific entity named "Komplete"

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Kom" and its variations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

lier

-0.82

Rah

-0.74

STATE

-0.73

liest

-0.73

âĸ¬

-0.71

++++++++++++++++

-0.71

angelo

-0.66

BOOK

-0.65

Rah

-0.64

POSITIVE LOGITS

merce

1.35

plete

1.20

puter

1.12

ittee

1.09

orph

1.03

obile

1.03

anical

1.03

mercial

1.02

obiles

1.02

ilitary

1.01

Activations Density 0.021%

proper nouns related to a specific entity named "Komplete"

mentions of the word "Kom" and its variations

No Comments

No Known Activations