INDEX

Explanations

person or thing associated with the letters "Se" followed by a numerical value of 9 or 10

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the character "Se" or variations of it in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

etheless

-0.79

CPC

-0.77

£ı

-0.69

 wire

-0.67

 diplom

-0.67

iants

-0.66

 Univ

-0.65

INGTON

-0.65

Downloadha

-0.65

 realism

-0.63

POSITIVE LOGITS

eker

1.18

vere

1.17

ldom

1.12

ethe

1.04

eps

1.01

asons

1.00

greg

0.98

isse

0.96

venth

0.96

emed

0.94

Activations Density 0.012%

person or thing associated with the letters "Se" followed by a numerical value of 9 or 10

repeated mentions of the character "Se" or variations of it in context

No Comments

No Known Activations