INDEX

Explanations

phrases related to proximity or closeness

oai_token-act-pair · gpt-3.5-turbo

references to proximity or closeness in relation to various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ury

-0.80

Ĥª

-0.70

*/(

-0.67

 Cosponsors

-0.66

©¶æ¥µ

-0.65

Ļ

-0.65

birds

-0.64

 Edited

-0.63

æ©

-0.63

kai

-0.62

POSITIVE LOGITS

 shore

1.04

sighted

0.87

 perfection

0.87

 midnight

0.75

 completion

0.75

shore

0.72

 home

0.72

 fruition

0.70

 achieving

0.70

 extinction

0.69

Activations Density 0.073%

phrases related to proximity or closeness

references to proximity or closeness in relation to various subjects

No Comments

No Known Activations