INDEX

Explanations

references to patrons or patronizing behaviors

oai_token-act-pair · gpt-3.5-turbo

terms associated with the concept of a "patron" and its various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

MO

-0.78

DX

-0.72

grass

-0.72

ARR

-0.71

REE

-0.70

eva

-0.70

expensive

-0.68

nesota

-0.67

ARB

-0.66

sg

-0.65

POSITIVE LOGITS

 patrons

1.07

 patron

1.05

hetically

0.88

isance

0.86

 Patron

0.73

 saint

0.72

esses

0.71

iless

0.71

sth

0.71

ãĥĩãĤ£

0.70

Activations Density 0.008%

references to patrons or patronizing behaviors

terms associated with the concept of a "patron" and its various forms

No Comments

No Known Activations