INDEX

Explanations

phrases related to specific geographical areas or locations

oai_token-act-pair · gpt-3.5-turbo

references to the concept of surrounding or nearby areas

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

err

-0.72

IFIC

-0.70

iasis

-0.69

ository

-0.69

inker

-0.68

inen

-0.67

ifiable

-0.66

oria

-0.66

uld

-0.66

assian

-0.66

POSITIVE LOGITS

 Thumbnails

0.67

tones

0.62

 jurisdictions

0.62

 Leone

0.62

 defences

0.60

 Admir

0.60

cules

0.60

 developments

0.59

 envelop

0.59

 communities

0.59

Activations Density 0.018%

phrases related to specific geographical areas or locations

references to the concept of surrounding or nearby areas

No Comments

No Known Activations