INDEX

Explanations

phrases related to making decisions or taking actions

oai_token-act-pair · gpt-3.5-turbo

words related to decision-making and agreements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

iaries

-0.73

urches

-0.72

ories

-0.71

 finances

-0.69

 brackets

-0.69

 disciplines

-0.69

 raids

-0.68

 classes

-0.68

itudes

-0.66

drops

-0.65

POSITIVE LOGITS

 somewhere

0.82

DragonMagazine

0.76

dylib

0.75

atical

0.75

 whereby

0.75

 apiece

0.72

like

0.71

ogram

0.68

earance

0.66

OSP

0.65

Activations Density 0.313%

phrases related to making decisions or taking actions

words related to decision-making and agreements

No Comments

No Known Activations