INDEX

Explanations

locations and events such as churches, community centers, and theaters

oai_token-act-pair · gpt-3.5-turbo

specific locations or venues 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

speak

-0.79

verbs

-0.79

govtrack

-0.76

measures

-0.75

thia

-0.75

stories

-0.72

pun

-0.68

riel

-0.68

 Lanka

-0.68

++;

-0.67

POSITIVE LOGITS

 Hotel

1.41

 hotel

1.22

 courthouse

1.19

 Museum

1.15

 facility

1.14

 Resort

1.13

 campus

1.12

 Coliseum

1.09

 plaza

1.09

 entrance

1.07

Activations Density 0.306%

locations and events such as churches, community centers, and theaters

specific locations or venues mentioned in the text

No Comments

No Known Activations