INDEX

Explanations

the name "Owen" with varying degrees of relevance

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Owen" 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 @ 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

pmwiki

-0.81

ĺħ

-0.80

cffff

-0.71

 practicable

-0.70

£ı

-0.70

ocre

-0.70

Ĥª

-0.69

senal

-0.68

 mathemat

-0.67

 suscept

-0.67

POSITIVE LOGITS

wen

1.12

borough

0.97

 PsyNet

0.88

burn

0.86

 Kenobi

0.85

yk

0.83

mere

0.82

urst

0.82

chen

0.81

jen

0.79

Activations Density 0.007%

the name "Owen" with varying degrees of relevance

occurrences of the name "Owen" and related terms

No Comments

No Known Activations