INDEX

Explanations

The neuron is looking for author attribution indicators

oai_token-act-pair · gpt-3.5-turbo

references to authors or contributors in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 pains

-0.88

itives

-0.78

hement

-0.73

 retard

-0.70

bler

-0.69

 realised

-0.65

blers

-0.65

 realise

-0.64

 manif

-0.63

pler

-0.63

POSITIVE LOGITS

akuya

0.87

 virtue

0.82

pass

0.79

catch

0.73

Author

0.72

stand

0.71

CAR

0.67

 downloading

0.65

 Email

0.65

Title

0.65

Activations Density 0.037%

The neuron is looking for author attribution indicators

references to authors or contributors in the text

No Comments

No Known Activations