INDEX

Explanations

locations or venues in cities

oai_token-act-pair · gpt-3.5-turbo

locations mentioned in the text

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

-0.71

henko

-0.69

*/

-0.69

Äĩ

-0.65

hole

-0.65

ãĥĩ

-0.64

merga

-0.63

 Logged

-0.60

Xie

-0.60

dj

-0.60

POSITIVE LOGITS

 Newark

1.14

 Arlington

1.14

 Philadelphia

1.11

 downtown

1.07

 Manhattan

1.04

 Washington

1.03

 Alexandria

1.03

 Pasadena

1.02

 Louisville

1.02

 Chicago

1.02

Activations Density 0.102%

locations or venues in cities

locations mentioned in the text

No Known Activations