INDEX

Explanations

references to photos (oto)

oai_token-act-pair · gpt-3.5-turbo

references to photos or images

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

acious

-0.74

acity

-0.74

hip

-0.72

ness

-0.71

sheet

-0.70

nesses

-0.70

rity

-0.70

iments

-0.69

ials

-0.67

 saline

-0.65

POSITIVE LOGITS

zzi

1.35

veland

0.96

========

0.88

zzo

0.85

============

0.82

onga

0.82

hene

0.80

arty

0.78

redo

0.78

amera

0.77

Activations Density 0.031%

references to photos (oto)

references to photos or images

No Comments

No Known Activations