INDEX

Explanations

instances where something or someone is distinguished as the sole or primary entity in a particular context

oai_token-act-pair · gpt-3.5-turbo

phrases indicating something is unique or one of many

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

excluding

-0.65

 Respect

-0.64

 Skydragon

-0.64

Progress

-0.63

hyd

-0.63

isters

-0.62

houses

-0.61

remember

-0.60

 GENERAL

-0.60

ocene

-0.60

POSITIVE LOGITS

 bottleneck

0.70

 anymore

0.69

cyn

0.67

 sidel

0.64

nor

0.64

 irony

0.63

.}

0.63

£ı

0.62

 complication

0.60

 harb

0.60

Activations Density 0.058%

instances where something or someone is distinguished as the sole or primary entity in a particular context

phrases indicating something is unique or one of many

No Comments

No Known Activations