INDEX

Explanations

locations and proper nouns

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or geographic features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ITCH

-0.77

cause

-0.75

etheless

-0.75

 Patreon

-0.72

!:

-0.66

¶ħ

-0.65

availability

-0.64

[/

-0.63

>:

-0.62

[/

-0.61

POSITIVE LOGITS

 resides

1.16

 resided

1.01

 reside

0.92

 shines

0.91

 intersect

0.86

 meets

0.85

 belongs

0.84

 awaited

0.84

 enters

0.84

 originated

0.81

Activations Density 0.368%

locations and proper nouns

references to specific locations or geographic features

No Comments

No Known Activations