INDEX

Explanations

phrases indicating sudden or unexpected events

oai_token-act-pair · gpt-3.5-turbo

key moments of confusion or absurdity in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

quartered

-0.70

ardless

-0.68

beit

-0.67

 withstand

-0.66

eele

-0.64

tein

-0.63

edIn

-0.62

)]

-0.62

 preserved

-0.61

INGTON

-0.61

POSITIVE LOGITS

 again

1.16

 Suddenly

1.05

Suddenly

1.04

again

0.95

 abruptly

0.94

 anew

0.90

 suddenly

0.87

 uncontroll

0.86

uddenly

0.85

 culminating

0.79

Activations Density 0.763%

phrases indicating sudden or unexpected events

key moments of confusion or absurdity in narratives

No Comments

No Known Activations