INDEX

Explanations

pronouns indicating possession

oai_token-act-pair · gpt-3.5-turbo

possessive pronouns indicating ownership or belonging

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

gravity

-0.74

establishment

-0.70

positive

-0.69

iple

-0.67

erate

-0.67

Edge

-0.63

lined

-0.63

edd

-0.62

orsi

-0.62

trump

-0.62

POSITIVE LOGITS

selves

1.04

self

0.90

creen

0.74

uria

0.71

ovie

0.69

RPG

0.68

 hers

0.67

tam

0.65

 theirs

0.64

 ours

0.64

Activations Density 0.013%

pronouns indicating possession

possessive pronouns indicating ownership or belonging

No Comments

No Known Activations