INDEX

Explanations

phrases related to occurrences, incidents, or documented cases

oai_token-act-pair · gpt-3.5-turbo

references to various types of cases or instances involving events or situations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

asus

-0.82

argon

-0.79

aye

-0.73

sonian

-0.73

bern

-0.67

atomic

-0.67

phia

-0.66

bush

-0.64

pole

-0.62

ebus

-0.62

POSITIVE LOGITS

 involving

1.23

hots

0.91

 thereof

0.87

 where

0.87

 wherein

0.86

 cases

0.84

 occurring

0.80

 cited

0.79

 documented

0.79

icles

0.78

Activations Density 0.096%

phrases related to occurrences, incidents, or documented cases

references to various types of cases or instances involving events or situations

No Comments

No Known Activations