INDEX

Explanations

words related to leftovers, remains, or profits

oai_token-act-pair · gpt-3.5-turbo

phrases related to remnants or leftovers from previous events or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

hess

-0.70

âľ

-0.69

idelines

-0.68

uffer

-0.66

Contents

-0.66

ationally

-0.65

Wide

-0.65

perty

-0.64

limits

-0.64

picture

-0.63

POSITIVE LOGITS

 deceased

0.93

 previous

0.90

 childhood

0.75

 defunct

0.72

 ancestral

0.71

 fallen

0.71

 salv

0.71

old

0.70

 scaven

0.67

 youth

0.67

Activations Density 0.437%

words related to leftovers, remains, or profits

phrases related to remnants or leftovers from previous events or contexts

No Comments

No Known Activations