INDEX

Explanations

phrases related to possessive pronouns followed by descriptive words or nouns

oai_token-act-pair · gpt-3.5-turbo

possessive pronouns and indicators of ownership or affiliation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

epad

-0.78

illac

-0.76

omial

-0.74

inventoryQuantity

-0.71

ibaba

-0.70

isp

-0.68

SHIP

-0.67

inction

-0.67

rency

-0.65

$$$$

-0.64

POSITIVE LOGITS

 followers

1.67

 listeners

1.61

 peers

1.61

 colleagues

1.59

 detractors

1.59

 readers

1.57

 customers

1.56

 constituents

1.54

 adversaries

1.53

 clients

1.53

Activations Density 0.202%

phrases related to possessive pronouns followed by descriptive words or nouns

possessive pronouns and indicators of ownership or affiliation

No Comments

No Known Activations