INDEX

Explanations

words related to electronic devices or technology specifically in the context of reviews or evaluations

oai_token-act-pair · gpt-3.5-turbo

names of specific products or devices

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

imeters

-0.67

scrib

-0.67

weather

-0.66

cmp

-0.63

paren

-0.63

¶ħ

-0.61

é¾įå¥ĳå£«

-0.61

mir

-0.59

ĳå£«

-0.59

 Glas

-0.59

POSITIVE LOGITS

 itself

0.92

 moniker

0.84

 bandwagon

0.81

 Awakens

0.80

 logo

0.77

ariat

0.72

 Implementation

0.72

mma

0.72

 salute

0.71

 enclosure

0.70

Activations Density 0.280%

words related to electronic devices or technology specifically in the context of reviews or evaluations

names of specific products or devices

No Comments

No Known Activations