INDEX

Explanations

instances where the word "patron" or its variations are mentioned

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "patronage."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

DX

-0.91

LOD

-0.81

nesota

-0.77

RAM

-0.73

ARR

-0.72

ARB

-0.72

AR

-0.72

REE

-0.69

EVA

-0.68

eva

-0.68

POSITIVE LOGITS

 patron

1.29

 patrons

1.00

 Patron

0.95

isance

0.89

 saint

0.81

hetically

0.78

ising

0.75

 sidx

0.75

ãĥ¼ãĥĨ

0.74

ised

0.74

Activations Density 0.005%

instances where the word "patron" or its variations are mentioned

references to the concept of "patronage."

No Comments

No Known Activations