INDEX

Explanations

the name "Dominic" or any variations of it

oai_token-act-pair · gpt-3.5-turbo

references to the word "Dominic" and related terms

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

ONSORED

-0.76

packing

-0.74

ynthesis

-0.71

dream

-0.67

RAY

-0.65

side

-0.64

 Hath

-0.64

OUT

-0.64

road

-0.63

ppo

-0.63

POSITIVE LOGITS

ance

1.01

antly

0.97

encies

0.91

ant

0.91

antine

0.89

ANCE

0.89

ator

0.89

orian

0.89

ainer

0.88

ique

0.86

Activations Density 0.015%

the name "Dominic" or any variations of it

references to the word "Dominic" and related terms

No Comments

No Known Activations