INDEX

Explanations

titles or headings with specific keywords

oai_token-act-pair · gpt-3.5-turbo

terms related to headings or titles in structured documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

icer

-0.67

arching

-0.66

 Slaughter

-0.62

conservancy

-0.61

ittal

-0.60

 Simulator

-0.60

 fruitful

-0.60

 sizeable

-0.59

qua

-0.57

ngth

-0.57

POSITIVE LOGITS

=""

0.80

 Dictionary

0.79

Â¯

0.76

lua

0.73

bsite

0.69

sic

0.69

ãĤ´ãĥ³

0.68

Said

0.68

="

0.67

soDeliveryDate

0.67

Activations Density 0.303%

titles or headings with specific keywords

terms related to headings or titles in structured documents

No Comments

No Known Activations