INDEX

Explanations

The main thing this neuron does is find expressions that mention years

oai_token-act-pair · gpt-3.5-turbo

specific references to media, events, and entities associated with pop culture and sports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 assorted

-0.57

 Undead

-0.53

onomy

-0.52

zi

-0.51

Magn

-0.51

accompanied

-0.51

aughed

-0.51

ãĥ©ãĥ³

-0.50

liam

-0.50

arthy

-0.50

POSITIVE LOGITS

nor

2.24

 anymore

2.18

nor

1.64

 whatsoever

1.47

yet

1.34

 unless

1.25

 slightest

1.17

 anywhere

1.16

unless

1.14

any

1.13

Activations Density 0.938%

The main thing this neuron does is find expressions that mention years

specific references to media, events, and entities associated with pop culture and sports

No Comments

No Known Activations