INDEX

Explanations

phrases related to beginning or initiating tasks or projects

oai_token-act-pair · gpt-3.5-turbo

occurrences of the phrase "getting started."

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

bey

-0.76

dayName

-0.75

ighth

-0.74

orie

-0.71

ãĥ¼ãĥ³

-0.71

ajo

-0.68

phy

-0.67

atu

-0.67

 entirety

-0.65

oped

-0.65

POSITIVE LOGITS

 anew

0.77

nings

0.71

ESSION

0.66

 poking

0.66

 sketch

0.65

 STEP

0.65

 Casting

0.62

OCK

0.62

ners

0.62

 experimenting

0.61

Activations Density 0.021%

phrases related to beginning or initiating tasks or projects

occurrences of the phrase "getting started."

No Comments

No Known Activations