INDEX

Explanations

locations or geographic terms related to the West (e.g., West Virginia)

oai_token-act-pair · gpt-3.5-turbo

the repeated mention of the word "West," particularly in relation to West Virginia

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

etsk

-0.92

cffff

-0.77

displayText

-0.73

 confir

-0.71

 pinch

-0.69

staking

-0.68

Downloadha

-0.67

Æ

-0.67

uary

-0.64

aminer

-0.63

POSITIVE LOGITS

minster

1.23

chester

1.22

 Indies

1.19

lake

1.13

cott

1.13

 Coast

1.11

fall

1.09

phal

1.08

side

1.07

bury

1.05

Activations Density 0.029%

locations or geographic terms related to the West (e.g., West Virginia)

the repeated mention of the word "West," particularly in relation to West Virginia

No Comments

No Known Activations