INDEX

Explanations

terms related to possession or ownership

oai_token-act-pair · gpt-3.5-turbo

the term "holder" and its variations, indicating references to ownership or possession

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

eller

-0.74

romy

-0.71

schild

-0.69

clusions

-0.68

urer

-0.68

enic

-0.66

 Reaper

-0.64

ologist

-0.63

ebook

-0.62

okes

-0.62

POSITIVE LOGITS

holders

1.34

holder

1.13

 holders

1.05

 holder

0.88

TextColor

0.74

pring

0.74

holding

0.73

houses

0.72

pole

0.72

lein

0.70

Activations Density 0.033%

terms related to possession or ownership

the term "holder" and its variations, indicating references to ownership or possession

No Comments

No Known Activations