INDEX

Explanations

terms related to brain lobes, specifically the parietal lobe

oai_token-act-pair · gpt-3.5-turbo

anatomical terms associated with different brain regions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

iosyncr

-0.75

ipedia

-0.75

 Pyth

-0.72

yrinth

-0.72

illed

-0.71

iyah

-0.70

ancies

-0.70

WER

-0.70

agn

-0.69

yssey

-0.67

POSITIVE LOGITS

 lobe

1.22

 cortex

1.04

 Lumpur

0.85

 temporal

0.80

lob

0.77

 frontal

0.77

Ħ¢

0.74

 cort

0.72

ietal

0.72

 prefrontal

0.70

Activations Density 0.025%

terms related to brain lobes, specifically the parietal lobe

anatomical terms associated with different brain regions

No Comments

No Known Activations