INDEX

Explanations

technical data, such as numerical values and symbols

oai_token-act-pair · gpt-3.5-turbo

specific identifiers or indicators related to important numerical or health-related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 suspic

-0.64

interstitial

-0.59

ĨĴ

-0.55

QUIRE

-0.55

iren

-0.54

 confir

-0.54

ailability

-0.53

 bias

-0.53

 Frie

-0.53

vantage

-0.52

POSITIVE LOGITS

soDeliveryDate

0.70

 Leilan

0.66

Kik

0.64

lux

0.62

MpServer

0.59

 Chimera

0.56

 Baal

0.55

 Seraph

0.54

ahime

0.54

 kitten

0.53

Activations Density 1.407%

technical data, such as numerical values and symbols

specific identifiers or indicators related to important numerical or health-related contexts

No Comments

No Known Activations