INDEX

Explanations

phrases related to caution or warning

oai_token-act-pair · gpt-3.5-turbo

concepts related to conditions, requirements, and processes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

\":

-0.53

 whistleblower

-0.52

umbai

-0.49

DEBUG

-0.49

OOOOOOOO

-0.49

OPLE

-0.48

oros

-0.46

DragonMagazine

-0.46

 Panthers

-0.45

 Greenberg

-0.45

POSITIVE LOGITS

 unless

0.89

due

0.88

 afterwards

0.86

 whilst

0.82

 anyways

0.81

 anymore

0.80

 alike

0.80

 anyway

0.80

.[

0.79

0.78

Activations Density 0.736%

phrases related to caution or warning

concepts related to conditions, requirements, and processes in various contexts

No Comments

No Known Activations