INDEX

Explanations

references to entities or products associated with NN (Neural Networks)

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "NN" 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ocene

-0.77

toe

-0.74

rero

-0.68

 fracturing

-0.67

rano

-0.67

chnology

-0.66

 Hiroshima

-0.65

boarding

-0.65

staking

-0.64

rosse

-0.62

POSITIVE LOGITS

nn

1.08

NN

0.97

aturally

0.92

erd

0.87

ipeg

0.84

hari

0.82

ominated

0.82

aught

0.80

eus

0.80

jad

0.78

Activations Density 0.010%

references to entities or products associated with NN (Neural Networks)

occurrences of the term "NN" and its variations

No Comments

No Known Activations