INDEX

Explanations

references to companionship or companions

oai_token-act-pair · gpt-3.5-turbo

terms related to companionship and social connections

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

mberg

-0.80

 Abstract

-0.72

mination

-0.69

zers

-0.68

ming

-0.66

ftime

-0.65

ffen

-0.64

SOURCE

-0.63

©¶æ

-0.62

med

-0.62

POSITIVE LOGITS

hip

1.48

 companions

0.81

hips

0.79

ragon

0.75

piece

0.74

ively

0.72

 companion

0.72

 pets

0.72

ables

0.71

pieces

0.71

Activations Density 0.092%

references to companionship or companions

terms related to companionship and social connections

No Comments

No Known Activations