INDEX

Explanations

questions starting with "Where" and followed by a verb

oai_token-act-pair · gpt-3.5-turbo

questions or prompts related to location or direction

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

lish

-0.64

 âĹı

-0.63

teness

-0.63

cycle

-0.63

\\\\\\\\\\\\\\\\

-0.62

letters

-0.61

HCR

-0.60

bear

-0.60

Fas

-0.58

atform

-0.58

POSITIVE LOGITS

 intersect

0.82

Interstitial

0.74

 awaited

0.74

 surrounded

0.70

 geographically

0.70

 invaded

0.69

 boarded

0.68

abouts

0.67

REDACTED

0.67

SPONSORED

0.66

Activations Density 0.305%

questions starting with "Where" and followed by a verb

questions or prompts related to location or direction

No Comments

No Known Activations