INDEX

Explanations

terms related to romantic or affectionate relationships

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

terms related to emotional or romantic relationships

oai_token-act-pair · gpt-3.5-turbo

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

 rudimentary

-0.75

SPONSORED

-0.74

UL

-0.73

ural

-0.71

ulhu

-0.71

é¾

-0.70

printed

-0.70

edu

-0.66

 administration

-0.64

©¶æ

-0.63

POSITIVE LOGITS

lihood

0.87

hip

0.81

ongs

0.78

hips

0.74

ync

0.74

nesday

0.73

club

0.72

 Swap

0.70

 Pair

0.70

omed

0.69

Activations Density 0.011%

terms related to romantic or affectionate relationships

terms related to emotional or romantic relationships

No Comments

No Known Activations