INDEX

Explanations

phrases related to specific entities or brands

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of places, organizations, and entertainment references

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

)=(

-0.72

¶ħ

-0.68

hement

-0.68

anwhile

-0.67

mble

-0.60

assetsadobe

-0.59

,,,,

-0.59

 ..........

-0.59

 unloaded

-0.58

 headlights

-0.57

POSITIVE LOGITS

 Continent

0.65

Fest

0.63

 Eden

0.63

Era

0.62

verse

0.61

Wiki

0.61

opia

0.60

 Island

0.60

 experien

0.60

$.

0.59

Activations Density 0.852%

phrases related to specific entities or brands

proper nouns, particularly names of places, organizations, and entertainment references

No Comments

No Known Activations