INDEX

Explanations

phrases related to locations or physical entities

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in" and phrases indicating location or positioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 disappoint

-0.68

anx

-0.65

pin

-0.64

 mell

-0.64

esson

-0.61

 accounted

-0.59

sticks

-0.59

appers

-0.58

tug

-0.58

 impressions

-0.57

POSITIVE LOGITS

 Bangalore

0.89

accessible

0.74

 Canberra

0.74

 conjunction

0.73

 behalf

0.73

 lieu

0.71

 Bangkok

0.70

 Chattanooga

0.69

 Islamabad

0.69

 Bulgaria

0.68

Activations Density 0.402%

phrases related to locations or physical entities

occurrences of the word "in" and phrases indicating location or positioning

No Comments

No Known Activations