INDEX

Explanations

descriptions of physical altercations or conflicts

oai_token-act-pair · gpt-3.5-turbo

descriptions of violent confrontations or struggles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

uably

-0.72

etheless

-0.69

ocally

-0.65

iterranean

-0.63

 honoured

-0.62

 inher

-0.62

å¥³

-0.61

 EDITION

-0.61

çīĪ

-0.60

 descendants

-0.59

POSITIVE LOGITS

 startled

0.78

 panicked

0.71

 takedown

0.68

 gunfire

0.64

Stop

0.63

Suddenly

0.63

 unconscious

0.63

 hurried

0.61

 agitated

0.61

 grabbed

0.61

Activations Density 1.018%

descriptions of physical altercations or conflicts

descriptions of violent confrontations or struggles

No Comments

No Known Activations