INDEX

Explanations

instances where clarification or explanation is needed

oai_token-act-pair · gpt-3.5-turbo

terms related to clarification or the need to provide explanations

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

Not in Any Lists

No Comments

Negative Logits

onna

-0.73

ãĥĦ

-0.70

geoning

-0.69

azo

-0.68

cano

-0.66

hani

-0.65

 teasp

-0.64

quartered

-0.62

ractor

-0.62

kas

-0.62

POSITIVE LOGITS

 everything

1.27

why

1.27

 what

1.24

 whats

1.20

WHY

1.11

 exactly

1.07

why

1.03

 things

1.02

 specifics

1.01

how

1.00

Activations Density 0.262%

instances where clarification or explanation is needed

terms related to clarification or the need to provide explanations

No Comments

No Known Activations