INDEX

Explanations

pronouns and words related to possession

oai_token-act-pair · gpt-3.5-turbo

references to entities, particularly people and pronouns, in a text

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

 Jobs

-0.65

 Cabin

-0.63

ashtra

-0.59

 Rahul

-0.58

æ©Ł

-0.58

 Paradise

-0.57

 Pike

-0.57

dinand

-0.56

 Presence

-0.56

ospels

-0.56

POSITIVE LOGITS

 regards

0.94

 regard

0.84

 impunity

0.82

ilst

0.78

holding

0.70

draw

0.70

 guiActiveUn

0.68

 utmost

0.68

amaz

0.67

 compr

0.65

Activations Density 0.155%

pronouns and words related to possession

references to entities, particularly people and pronouns, in a text

No Comments

No Known Activations