INDEX

Explanations

specific entities or names containing the letters "NR" followed by a digit

oai_token-act-pair · gpt-3.5-turbo

mentions of "NR" followed by numbers, indicating a focus on specific ratings or identifiers

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

 congr

-0.77

 Metatron

-0.70

 Izan

-0.67

 undone

-0.65

dates

-0.64

Minecraft

-0.61

heartedly

-0.61

 Fairfax

-0.61

forcing

-0.60

 Villa

-0.60

POSITIVE LOGITS

NR

0.91

UTH

0.80

ACK

0.79

NR

0.79

otiation

0.77

yss

0.75

OST

0.75

ud

0.74

ativity

0.74

UV

0.73

Activations Density 0.022%

specific entities or names containing the letters "NR" followed by a digit

mentions of "NR" followed by numbers, indicating a focus on specific ratings or identifiers

No Comments

No Known Activations