INDEX

Explanations

proper names or specific terms

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of people and organizations

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

 clipboard

-0.72

 lockout

-0.65

Ö

-0.61

 alphabet

-0.59

 tripod

-0.59

 selfie

-0.59

ploma

-0.58

========

-0.58

 pedal

-0.58

 totality

-0.58

POSITIVE LOGITS

 said

0.77

anson

0.72

pecially

0.72

orio

0.71

 argues

0.69

 says

0.68

said

0.67

wise

0.67

 spokeswoman

0.67

gui

0.67

Activations Density 0.311%

proper names or specific terms

proper nouns, particularly names of people and organizations

No Comments

No Known Activations