INDEX

Explanations

words related to geographical locations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "en."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 hitch

-0.77

TPPStreamerBot

-0.73

enhagen

-0.68

 Canaveral

-0.68

 reconc

-0.67

ONSORED

-0.63

 reluct

-0.62

 shake

-0.62

 Haram

-0.62

milo

-0.62

POSITIVE LOGITS

emies

1.28

chant

1.18

riched

1.12

zyme

1.06

wald

1.06

ews

1.02

emy

1.00

esis

0.97

forced

0.97

bach

0.96

Activations Density 0.038%

words related to geographical locations

occurrences of the word "en."

No Comments

No Known Activations