INDEX

Explanations

phrases related to the concept of depth or deepness

oai_token-act-pair · gpt-3.5-turbo

references to popular culture and media, particularly related to deep issues and concepts

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

apest

-0.92

iard

-0.73

 Palest

-0.73

jee

-0.71

Yel

-0.69

 GEAR

-0.67

TAG

-0.66

Zup

-0.65

lez

-0.65

 Scrib

-0.64

POSITIVE LOGITS

 depths

0.79

 horizont

0.75

ibur

0.73

 penetrating

0.71

ngth

0.69

 breadth

0.67

 Detected

0.66

 depth

0.66

 deepest

0.65

learning

0.65

Activations Density 0.119%

phrases related to the concept of depth or deepness

references to popular culture and media, particularly related to deep issues and concepts

No Comments

No Known Activations