INDEX

Explanations

references to furniture, particularly items found next to a bed

oai_token-act-pair · gpt-3.5-turbo

phrases and concepts related to endings and concluding moments

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

anson

-0.94

alg

-0.87

ickr

-0.77

educ

-0.75

abase

-0.74

Reviewer

-0.74

char

-0.72

Asset

-0.72

OY

-0.72

irlf

-0.72

POSITIVE LOGITS

 ceremony

0.70

 attendants

0.66

 anniversary

0.66

 devastation

0.64

 misery

0.63

 festivities

0.62

 reception

0.62

 fences

0.61

 celebration

0.60

 truce

0.60

Activations Density 0.176%

references to furniture, particularly items found next to a bed

phrases and concepts related to endings and concluding moments

No Comments

No Known Activations