INDEX

Explanations

instances of doubled or doubling in various contexts

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept of doubling or increasing quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ä½ľ

-0.76

çĦ

-0.75

Services

-0.71

hra

-0.70

Ö¼

-0.69

ãĤĬ

-0.69

utic

-0.68

é¾

-0.67

Interstitial

-0.66

lder

-0.64

POSITIVE LOGITS

 digit

0.75

 tripled

0.74

amp

0.71

peak

0.70

 exponentially

0.70

assis

0.70

 doubled

0.67

ouble

0.66

 dipping

0.66

 heating

0.65

Activations Density 0.012%

instances of doubled or doubling in various contexts

terms related to the concept of doubling or increasing quantities

No Comments

No Known Activations