INDEX

Explanations

phrases related to instructions or directives

oai_token-act-pair · gpt-3.5-turbo

the word "the" and variations in its 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

SPONSORED

-0.78

-0.69

 according

-0.66

âĢł

-0.64

iffe

-0.63

leeve

-0.62

 thereby

-0.62

 owing

-0.61

FILE

-0.61

Malley

-0.60

POSITIVE LOGITS

 same

1.20

 slightest

1.17

 simplest

1.16

 smallest

1.11

 hardest

1.11

 proverbial

1.10

 entire

1.08

 easiest

1.06

ses

1.05

 whole

1.04

Activations Density 2.041%

phrases related to instructions or directives

the word "the" and variations in its context

No Comments

No Known Activations